mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

update test results

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-10-03 19:04:02 +02:00
parent 2784d9c3b5
commit b3293ffc75
24 changed files with 184 additions and 198 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/data_scanned/scanned_01.easyocr.doctags.txt
View File

@ -1,5 +1,5 @@
<document> <document>
<subtitle-level-1><location><page_1><loc_21><loc_84><loc_76><loc_87></location>TableFormer: Table Structure Understanding with Transformers</subtitle-level-1> <subtitle-level-1><location><page_1><loc_21><loc_83><loc_76><loc_87></location>TableFormer: Table Structure Understanding with Transformers</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_78><loc_29><loc_80></location>1. Details on the datasets</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_78><loc_29><loc_80></location>1. Details on the datasets</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_76><loc_25><loc_78></location>1.1. Data preparation</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_76><loc_25><loc_78></location>1.1. Data preparation</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>As a first step of our data preparation process; we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes) A table is considered to be simple if it does not contain row spans or column spans. Addition ally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row Or column spans. Therefore a strict HTML structure looks always rectangular: However; HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity; which we want lo avoid. As such, we prefer to have strict" tables, i.e. tables where every row has exactly the same length.</paragraph> <paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>As a first step of our data preparation process; we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes) A table is considered to be simple if it does not contain row spans or column spans. Addition ally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row Or column spans. Therefore a strict HTML structure looks always rectangular: However; HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity; which we want lo avoid. As such, we prefer to have strict" tables, i.e. tables where every row has exactly the same length.</paragraph>
@ -7,8 +7,8 @@
<paragraph><location><page_1><loc_8><loc_18><loc_47><loc_21></location>Figure 7 illustrates the distribution of the tables across different dimensions per dataset.</paragraph> <paragraph><location><page_1><loc_8><loc_18><loc_47><loc_21></location>Figure 7 illustrates the distribution of the tables across different dimensions per dataset.</paragraph>
<subtitle-level-1><location><page_1><loc_8><loc_15><loc_25><loc_17></location>1.2. Synthetic datasets</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_15><loc_25><loc_17></location>1.2. Synthetic datasets</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_10><loc_47><loc_14></location>Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear -</paragraph> <paragraph><location><page_1><loc_8><loc_10><loc_47><loc_14></location>Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear -</paragraph>
<paragraph><location><page_1><loc_36><loc_82><loc_62><loc_85></location>Supplementary Material</paragraph> <subtitle-level-1><location><page_1><loc_36><loc_82><loc_62><loc_85></location>Supplementary Material</subtitle-level-1>
<paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O% , 109) . style Every</paragraph> <paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O%o , 109) . style Every</paragraph>
<paragraph><location><page_1><loc_50><loc_70><loc_89><loc_74></location>The process of generating a synthetic dataset can be decomposed into the following steps:</paragraph> <paragraph><location><page_1><loc_50><loc_70><loc_89><loc_74></location>The process of generating a synthetic dataset can be decomposed into the following steps:</paragraph>
<paragraph><location><page_1><loc_50><loc_60><loc_89><loc_71></location>1 Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances financial data, marketing data; etc.) Additionally; we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets PubTabNet, FinTabNet, etc.). (e.g (e.g</paragraph> <paragraph><location><page_1><loc_50><loc_60><loc_89><loc_71></location>1 Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances financial data, marketing data; etc.) Additionally; we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets PubTabNet, FinTabNet, etc.). (e.g (e.g</paragraph>
<paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>2 Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans ovCr multiple rows and table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans) maximum span size and the ratio of the table area covered by spans</paragraph> <paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>2 Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans ovCr multiple rows and table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans) maximum span size and the ratio of the table area covered by spans</paragraph>

2
tests/data_scanned/scanned_01.easyocr.json
View File

File diff suppressed because one or more lines are too long

4
tests/data_scanned/scanned_01.easyocr.md
View File

@ -14,9 +14,9 @@ Figure 7 illustrates the distribution of the tables across different dimensions
Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear - Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear -
Supplementary Material ## Supplementary Material
ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O% , 109) . style Every ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O%o , 109) . style Every
The process of generating a synthetic dataset can be decomposed into the following steps: The process of generating a synthetic dataset can be decomposed into the following steps:

2
tests/data_scanned/scanned_01.easyocr.pages.json
View File

File diff suppressed because one or more lines are too long

33
tests/data_scanned/scanned_01.tesseract.doctags.txt
View File

@ -1,20 +1,19 @@
<document> <document>
<subtitle-level-1><location><page_1><loc_21><loc_84><loc_76><loc_87></location>TableFormer: Table Structure Understanding with Transformers</subtitle-level-1> <subtitle-level-1><location><page_1><loc_22><loc_83><loc_76><loc_86></location>TableFormer: Table Structure Understanding with Transformers Supplementary Material</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_78><loc_29><loc_80></location>1. Details on the datasets</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_78><loc_29><loc_80></location>1. Details on the datasets</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_76><loc_25><loc_78></location>1.1. Data preparation</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_76><loc_25><loc_77></location>1.1. Data preparation</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>As a first step of our data preparation process; we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes) A table is considered to be simple if it does not contain row spans or column spans. Addition ally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row Or column spans. Therefore a strict HTML structure looks always rectangular: However; HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity; which we want lo avoid. As such, we prefer to have strict" tables, i.e. tables where every row has exactly the same length.</paragraph> <paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row or column spans. Therefore a strict HTML structure looks always rectangular. However, HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have "strict" tables, i.e. tables where every row has exactly the same length.</paragraph>
<paragraph><location><page_1><loc_8><loc_20><loc_47><loc_51></location>We have developed technique that tries to derive missing bounding box out of its neighbors. As a first step; we use the annotation data to generate the most fine'grained that covers the table structure. In case of strict HTML tables. all squares are associated with some table cell and in the presence of table spans a cell extends across mul tiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally; the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML ta bles is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 489 of the simple and 699 of the complex tables. RegardFinTabNet, 689 of the simple and 98% of the complex tables require the generation of bounding boxes grid grid ing</paragraph> <paragraph><location><page_1><loc_8><loc_21><loc_47><loc_51></location>We have developed a technique that tries to derive a missing bounding box out of its neighbors. As a first step, we use the annotation data to generate the most fine-grained grid that covers the table structure. In case of strict HTML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally, the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML tables is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 48% of the simple and 69% of the complex tables. Regarding FinTabNet, 68% of the simple and 98% of the complex tables require the generation of bounding boxes.</paragraph>
<paragraph><location><page_1><loc_8><loc_18><loc_47><loc_21></location>Figure 7 illustrates the distribution of the tables across different dimensions per dataset.</paragraph> <paragraph><location><page_1><loc_8><loc_18><loc_47><loc_20></location>Figure 7 illustrates the distribution of the tables across different dimensions per dataset.</paragraph>
<subtitle-level-1><location><page_1><loc_8><loc_15><loc_25><loc_17></location>1.2. Synthetic datasets</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_15><loc_25><loc_16></location>1.2. Synthetic datasets</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_10><loc_47><loc_14></location>Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear -</paragraph> <paragraph><location><page_1><loc_8><loc_10><loc_47><loc_14></location>Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear-</paragraph>
<paragraph><location><page_1><loc_36><loc_82><loc_62><loc_85></location>Supplementary Material</paragraph> <paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>ances in regard to their size, structure, style and content. Every synthetic dataset contains 150k examples, summing up to 600k synthetic examples. All datasets are divided into Train, Test and Val splits (80%, 10%, 10%).</paragraph>
<paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O% , 109) . style Every</paragraph> <paragraph><location><page_1><loc_50><loc_71><loc_89><loc_73></location>The process of generating a synthetic dataset can be decomposed into the following steps:</paragraph>
<paragraph><location><page_1><loc_50><loc_70><loc_89><loc_74></location>The process of generating a synthetic dataset can be decomposed into the following steps:</paragraph> <paragraph><location><page_1><loc_50><loc_60><loc_89><loc_70></location>1. Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data, marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets (e.g. PubTabNet, FinTabNet, etc.).</paragraph>
<paragraph><location><page_1><loc_50><loc_60><loc_89><loc_71></location>1 Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances financial data, marketing data; etc.) Additionally; we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets PubTabNet, FinTabNet, etc.). (e.g (e.g</paragraph> <paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>2. Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header -body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans.</paragraph>
<paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>2 Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans ovCr multiple rows and table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans) maximum span size and the ratio of the table area covered by spans</paragraph> <paragraph><location><page_1><loc_50><loc_37><loc_89><loc_43></location>3. Generate content: Based on the dataset theme, a set of suitable content templates is chosen first. Then, this content can be combined with purely random text to produce the synthetic content.</paragraph>
<paragraph><location><page_1><loc_50><loc_37><loc_89><loc_43></location>3 Generate content: Based on the dataset theme. a set of suitable content templates is chosen first. Then; this content can be combined with purely random text to produce the synthetic content.</paragraph> <paragraph><location><page_1><loc_50><loc_31><loc_89><loc_37></location>4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates is first manually selected. Then, a style is randomly selected to format the appearance of the synthesized table.</paragraph>
<paragraph><location><page_1><loc_50><loc_31><loc_89><loc_37></location>4 Apply styling templates: Depending on the domain of the synthetic dataset; a set of styling templates is first manually selected Then, style is randomly selected to format the appearance of the synthesized table.</paragraph> <paragraph><location><page_1><loc_50><loc_23><loc_89><loc_31></location>5. Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process.</paragraph>
<paragraph><location><page_1><loc_50><loc_23><loc_89><loc_31></location>5 Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process.</paragraph> <subtitle-level-1><location><page_1><loc_50><loc_18><loc_89><loc_22></location>2. Prediction post-processing for PDF documents</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_50><loc_18><loc_89><loc_22></location>2. Prediction post-processing for PDF documents</subtitle-level-1> <paragraph><location><page_1><loc_50><loc_10><loc_89><loc_17></location>Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF documents, this is not enough when a full reconstruction of the original table is required. This happens mainly due the following reasons:</paragraph>
<paragraph><location><page_1><loc_50><loc_9><loc_89><loc_17></location>Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF docu ments, this is not enough when a full reconstruction of the original table is required. This happens mainly due the folrcasons: lowing7</paragraph>
</document> </document>

2
tests/data_scanned/scanned_01.tesseract.json
View File

File diff suppressed because one or more lines are too long

26
tests/data_scanned/scanned_01.tesseract.md
View File

@ -1,35 +1,33 @@
## TableFormer: Table Structure Understanding with Transformers ## TableFormer: Table Structure Understanding with Transformers Supplementary Material
## 1. Details on the datasets ## 1. Details on the datasets
## 1.1. Data preparation ## 1.1. Data preparation
As a first step of our data preparation process; we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes) A table is considered to be simple if it does not contain row spans or column spans. Addition ally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row Or column spans. Therefore a strict HTML structure looks always rectangular: However; HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity; which we want lo avoid. As such, we prefer to have strict" tables, i.e. tables where every row has exactly the same length. As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row or column spans. Therefore a strict HTML structure looks always rectangular. However, HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have "strict" tables, i.e. tables where every row has exactly the same length.
We have developed technique that tries to derive missing bounding box out of its neighbors. As a first step; we use the annotation data to generate the most fine'grained that covers the table structure. In case of strict HTML tables. all squares are associated with some table cell and in the presence of table spans a cell extends across mul tiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally; the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML ta bles is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 489 of the simple and 699 of the complex tables. RegardFinTabNet, 689 of the simple and 98% of the complex tables require the generation of bounding boxes grid grid ing We have developed a technique that tries to derive a missing bounding box out of its neighbors. As a first step, we use the annotation data to generate the most fine-grained grid that covers the table structure. In case of strict HTML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally, the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML tables is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 48% of the simple and 69% of the complex tables. Regarding FinTabNet, 68% of the simple and 98% of the complex tables require the generation of bounding boxes.
Figure 7 illustrates the distribution of the tables across different dimensions per dataset. Figure 7 illustrates the distribution of the tables across different dimensions per dataset.
## 1.2. Synthetic datasets ## 1.2. Synthetic datasets
Aiming t0 train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets_ Each one contains tables with different appear - Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear-
Supplementary Material ances in regard to their size, structure, style and content. Every synthetic dataset contains 150k examples, summing up to 600k synthetic examples. All datasets are divided into Train, Test and Val splits (80%, 10%, 10%).
ances in regard to their size; structure, and content. synthetic dataset contains 150k examples, summing up to 60Ok synthetic examples. All datasets are divided into Train; Test and Val splits (8O%, 1O% , 109) . style Every
The process of generating a synthetic dataset can be decomposed into the following steps: The process of generating a synthetic dataset can be decomposed into the following steps:
1 Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances financial data, marketing data; etc.) Additionally; we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets PubTabNet, FinTabNet, etc.). (e.g (e.g 1. Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data, marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets (e.g. PubTabNet, FinTabNet, etc.).
2 Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans ovCr multiple rows and table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans) maximum span size and the ratio of the table area covered by spans 2. Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header -body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans.
3 Generate content: Based on the dataset theme. a set of suitable content templates is chosen first. Then; this content can be combined with purely random text to produce the synthetic content. 3. Generate content: Based on the dataset theme, a set of suitable content templates is chosen first. Then, this content can be combined with purely random text to produce the synthetic content.
4 Apply styling templates: Depending on the domain of the synthetic dataset; a set of styling templates is first manually selected Then, style is randomly selected to format the appearance of the synthesized table. 4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates is first manually selected. Then, a style is randomly selected to format the appearance of the synthesized table.
5 Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process. 5. Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process.
## 2. Prediction post-processing for PDF documents ## 2. Prediction post-processing for PDF documents
Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF docu ments, this is not enough when a full reconstruction of the original table is required. This happens mainly due the folrcasons: lowing7 Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF documents, this is not enough when a full reconstruction of the original table is required. This happens mainly due the following reasons:

2
tests/data_scanned/scanned_01.tesseract.pages.json
View File

File diff suppressed because one or more lines are too long

41
tests/data_scanned/scanned_01.tesserocr.doctags.txt
View File

@ -1,20 +1,25 @@
<document> <document>
<subtitle-level-1><location><page_1><loc_22><loc_85><loc_76><loc_86></location>TableFormer: Table Structure Understanding with Transformers</subtitle-level-1> <paragraph><location><page_1><loc_8><loc_86><loc_47><loc_90></location>Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear-</paragraph>
<paragraph><location><page_1><loc_36><loc_83><loc_61><loc_85></location>Supplementary Material</paragraph> <subtitle-level-1><location><page_1><loc_8><loc_83><loc_89><loc_86></location>1.2. Synthetic datasets the bounding boxes for tables recognized inside PDF docu-</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_79><loc_29><loc_80></location>1. Details on the datasets</subtitle-level-1> <paragraph><location><page_1><loc_8><loc_80><loc_47><loc_82></location>Figure / illustrates the distribution of the tables across different dimensions per dataset.</paragraph>
<subtitle-level-1><location><page_1><loc_8><loc_76><loc_25><loc_77></location>1.1. Data preparation</subtitle-level-1> <subtitle-level-1><location><page_1><loc_8><loc_78><loc_39><loc_80></location>tables require the generation of bounding boxes.</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row or column spans. Therefore a strict HTML structure looks always rectangular. However, HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have "strict" tables, i.e. tables where every row has exactly the same length.</paragraph> <subtitle-level-1><location><page_1><loc_8><loc_76><loc_47><loc_78></location>ing FinlabNet, 68% of the simple and 98% of the complex</subtitle-level-1>
<paragraph><location><page_1><loc_8><loc_21><loc_47><loc_51></location>We have developed a technique that tries to derive a missing bounding box out of its neighbors. As a first step, we use the annotation data to generate the most fine-grained grid that covers the table structure. In case of strict HTML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally, the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML tables is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 48% of the simple and 69% of the complex tables. Regarding FinTabNet, 68% of the simple and 98% of the complex tables require the generation of bounding boxes.</paragraph> <paragraph><location><page_1><loc_8><loc_75><loc_47><loc_76></location>48% of the simple and 69% of the complex tables. Regard-</paragraph>
<paragraph><location><page_1><loc_8><loc_18><loc_47><loc_21></location>Figure 7 illustrates the distribution of the tables across different dimensions per dataset.</paragraph> <subtitle-level-1><location><page_1><loc_8><loc_76><loc_47><loc_78></location>ing FinlabNet, 68% of the simple and 98% of the complex</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_8><loc_15><loc_25><loc_16></location>1.2. Synthetic datasets</subtitle-level-1> <paragraph><location><page_1><loc_8><loc_51><loc_47><loc_75></location>missing bounding box out of its neighbors. As a first step. we use the annotation data to generate the most fine-grained erid that covers the table structure. In case of strict HIML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it 1s possible to compute the geometrical border lines between the grid rows and columns. Eventually this information 1s used to generate the missing bounding boxes. Additionally, the existence of unused grid Squares indicates that the table rows have unequal number of columns and the overall structure 1s non-strict. [he generation of missing bounding boxes for non-strict HI ML tables 1s ambiguous and therefore quite challenging. lhus, we have decided to simply discard those tables. In case of Pub labNet we have computed missing bounding boxes for</paragraph>
<paragraph><location><page_1><loc_8><loc_10><loc_47><loc_14></location>Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear-</paragraph> <paragraph><location><page_1><loc_8><loc_21><loc_47><loc_51></location>1.1. Data preparation As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured 1n the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HI ML structure 1f every row has the same number of columns after taking into account any row or column spans. [Therefore a strict HI ML structure looks always rectangular. However, HI ML 1s a lenient encoding format, 1.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. [hese implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have 'strict' tables, 1.e. tables where every row has exactly the same length. We have developed a technique that tries to derive a</paragraph>
<paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>ances in regard to their size, structure, style and content. Every synthetic dataset contains 150k examples, summing up to 600k synthetic examples. All datasets are divided into Train, Test and Val splits (80%, 10%, 10%).</paragraph> <paragraph><location><page_1><loc_8><loc_20><loc_29><loc_21></location>1. Details on the datasets</paragraph>
<paragraph><location><page_1><loc_50><loc_71><loc_89><loc_73></location>The process of generating a synthetic dataset can be decomposed into the following steps:</paragraph> <paragraph><location><page_1><loc_50><loc_86><loc_89><loc_90></location>ments, this 1s not enough when a full reconstruction of the original table 1s required. [his happens mainly due the following reasons</paragraph>
<paragraph><location><page_1><loc_50><loc_60><loc_89><loc_70></location>1. Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data, marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets (e.g. PubTabNet, FinTabNet, etc.).</paragraph> <subtitle-level-1><location><page_1><loc_52><loc_83><loc_89><loc_84></location>Although lableFormer can predict the table structure and</subtitle-level-1>
<paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>2. Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header -body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans.</paragraph> <paragraph><location><page_1><loc_53><loc_80><loc_58><loc_81></location>ments</paragraph>
<paragraph><location><page_1><loc_50><loc_37><loc_89><loc_43></location>3. Generate content: Based on the dataset theme, a set of suitable content templates is chosen first. Then, this content can be combined with purely random text to produce the synthetic content.</paragraph> <paragraph><location><page_1><loc_50><loc_74><loc_89><loc_80></location>utilized to optimize the runtime overhead of the rendering DIOCESS. 2. Prediction post-processing for PDF docu-</paragraph>
<paragraph><location><page_1><loc_50><loc_31><loc_89><loc_37></location>4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates is first manually selected. Then, a style is randomly selected to format the appearance of the synthesized table.</paragraph> <paragraph><location><page_1><loc_50><loc_71><loc_89><loc_74></location>finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique 1s</paragraph>
<paragraph><location><page_1><loc_50><loc_23><loc_89><loc_31></location>5. Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process.</paragraph> <paragraph><location><page_1><loc_50><loc_60><loc_89><loc_71></location>can be combined with purely random text to produce the synthetic content. 4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates 1s first manually selected. Ihen, a style is randomly selected to format the appearance of the synthesized table. 5. Render the complete tables: The synthetic table 1s</paragraph>
<subtitle-level-1><location><page_1><loc_50><loc_19><loc_89><loc_22></location>2. Prediction post-processing for PDF documents</subtitle-level-1> <paragraph><location><page_1><loc_50><loc_43><loc_89><loc_60></location>tentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header - body boundary. Ihe table structure 1s described by the parameters: Total number of table rows and columns. number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans. Generate content: Based on the dataset theme. a set of suitable content templates 1s chosen first. Then, this content</paragraph>
<paragraph><location><page_1><loc_50><loc_10><loc_89><loc_17></location>Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF documents, this is not enough when a full reconstruction of the original table is required. This happens mainly due the following reasons:</paragraph> <paragraph><location><page_1><loc_50><loc_37><loc_89><loc_43></location>frequently used terms out of non-synthetic datasets (e.g. Pub labNet, Fin LabNet, etc.). 2. Generate table structures: [he structure of each synthetic dataset assumes a horizontal table header which po-</paragraph>
<paragraph><location><page_1><loc_50><loc_31><loc_89><loc_37></location>templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data. marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most</paragraph>
<paragraph><location><page_1><loc_50><loc_23><loc_89><loc_31></location>up to 600K synthetic examples. All datasets are divided into Train, lest and Val splits (8O%, 10%, 10%). The process of generating a synthetic dataset can be decomposed into the following steps: |. Prepare styling and content templates: The styling</paragraph>
<paragraph><location><page_1><loc_50><loc_22><loc_89><loc_23></location>Every synthetic dataset contains 150k examples, summing</paragraph>
<subtitle-level-1><location><page_1><loc_50><loc_18><loc_89><loc_22></location>ances in regard to their size, structure, style and content.</subtitle-level-1>
<paragraph><location><page_1><loc_22><loc_10><loc_89><loc_17></location>TableFormer: Table Structure Understanding with Transformers Supplementary Material</paragraph>
</document> </document>

2
tests/data_scanned/scanned_01.tesserocr.json
View File

File diff suppressed because one or more lines are too long

60
tests/data_scanned/scanned_01.tesserocr.md
View File

@ -1,35 +1,45 @@
## TableFormer: Table Structure Understanding with Transformers
Supplementary Material
## 1. Details on the datasets
## 1.1. Data preparation
As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured in the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HTML structure if every row has the same number of columns after taking into account any row or column spans. Therefore a strict HTML structure looks always rectangular. However, HTML is a lenient encoding format, i.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. These implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have "strict" tables, i.e. tables where every row has exactly the same length.
We have developed a technique that tries to derive a missing bounding box out of its neighbors. As a first step, we use the annotation data to generate the most fine-grained grid that covers the table structure. In case of strict HTML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it is possible to compute the geometrical border lines between the grid rows and columns. Eventually this information is used to generate the missing bounding boxes. Additionally, the existence of unused grid squares indicates that the table rows have unequal number of columns and the overall structure is non-strict. The generation of missing bounding boxes for non-strict HTML tables is ambiguous and therefore quite challenging. Thus, we have decided to simply discard those tables. In case of PubTabNet we have computed missing bounding boxes for 48% of the simple and 69% of the complex tables. Regarding FinTabNet, 68% of the simple and 98% of the complex tables require the generation of bounding boxes.
Figure 7 illustrates the distribution of the tables across different dimensions per dataset.
## 1.2. Synthetic datasets
Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear- Aiming to train and evaluate our models in a broader spectrum of table data we have synthesized four types of datasets. Each one contains tables with different appear-
ances in regard to their size, structure, style and content. Every synthetic dataset contains 150k examples, summing up to 600k synthetic examples. All datasets are divided into Train, Test and Val splits (80%, 10%, 10%). ## 1.2. Synthetic datasets the bounding boxes for tables recognized inside PDF docu-
The process of generating a synthetic dataset can be decomposed into the following steps: Figure / illustrates the distribution of the tables across different dimensions per dataset.
1. Prepare styling and content templates: The styling templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data, marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most frequently used terms out of non-synthetic datasets (e.g. PubTabNet, FinTabNet, etc.). ## tables require the generation of bounding boxes.
2. Generate table structures: The structure of each synthetic dataset assumes a horizontal table header which potentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header -body boundary. The table structure is described by the parameters: Total number of table rows and columns, number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans. ## ing FinlabNet, 68% of the simple and 98% of the complex
3. Generate content: Based on the dataset theme, a set of suitable content templates is chosen first. Then, this content can be combined with purely random text to produce the synthetic content. 48% of the simple and 69% of the complex tables. Regard-
4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates is first manually selected. Then, a style is randomly selected to format the appearance of the synthesized table. ## ing FinlabNet, 68% of the simple and 98% of the complex
5. Render the complete tables: The synthetic table is finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique is utilized to optimize the runtime overhead of the rendering process. missing bounding box out of its neighbors. As a first step. we use the annotation data to generate the most fine-grained erid that covers the table structure. In case of strict HIML tables, all grid squares are associated with some table cell and in the presence of table spans a cell extends across multiple grid squares. When enough bounding boxes are known for a rectangular table, it 1s possible to compute the geometrical border lines between the grid rows and columns. Eventually this information 1s used to generate the missing bounding boxes. Additionally, the existence of unused grid Squares indicates that the table rows have unequal number of columns and the overall structure 1s non-strict. [he generation of missing bounding boxes for non-strict HI ML tables 1s ambiguous and therefore quite challenging. lhus, we have decided to simply discard those tables. In case of Pub labNet we have computed missing bounding boxes for
## 2. Prediction post-processing for PDF documents 1.1. Data preparation As a first step of our data preparation process, we have calculated statistics over the datasets across the following dimensions: (1) table size measured 1n the number of rows and columns, (2) complexity of the table, (3) strictness of the provided HTML structure and (4) completeness (i.e. no omitted bounding boxes). A table is considered to be simple if it does not contain row spans or column spans. Additionally, a table has a strict HI ML structure 1f every row has the same number of columns after taking into account any row or column spans. [Therefore a strict HI ML structure looks always rectangular. However, HI ML 1s a lenient encoding format, 1.e. tables with rows of different sizes might still be regarded as correct due to implicit display rules. [hese implicit rules leave room for ambiguity, which we want to avoid. As such, we prefer to have 'strict' tables, 1.e. tables where every row has exactly the same length. We have developed a technique that tries to derive a
Although TableFormer can predict the table structure and the bounding boxes for tables recognized inside PDF documents, this is not enough when a full reconstruction of the original table is required. This happens mainly due the following reasons: 1. Details on the datasets
ments, this 1s not enough when a full reconstruction of the original table 1s required. [his happens mainly due the following reasons
## Although lableFormer can predict the table structure and
ments
utilized to optimize the runtime overhead of the rendering DIOCESS. 2. Prediction post-processing for PDF docu-
finally rendered by a web browser engine to generate the bounding boxes for each table cell. A batching technique 1s
can be combined with purely random text to produce the synthetic content. 4. Apply styling templates: Depending on the domain of the synthetic dataset, a set of styling templates 1s first manually selected. Ihen, a style is randomly selected to format the appearance of the synthesized table. 5. Render the complete tables: The synthetic table 1s
tentially spans over multiple rows and a table body that may contain a combination of row spans and column spans. However, spans are not allowed to cross the header - body boundary. Ihe table structure 1s described by the parameters: Total number of table rows and columns. number of header rows, type of spans (header only spans, row only spans, column only spans, both row and column spans), maximum span size and the ratio of the table area covered by spans. Generate content: Based on the dataset theme. a set of suitable content templates 1s chosen first. Then, this content
frequently used terms out of non-synthetic datasets (e.g. Pub labNet, Fin LabNet, etc.). 2. Generate table structures: [he structure of each synthetic dataset assumes a horizontal table header which po-
templates have been manually designed and organized into groups of scope specific appearances (e.g. financial data. marketing data, etc.) Additionally, we have prepared curated collections of content templates by extracting the most
up to 600K synthetic examples. All datasets are divided into Train, lest and Val splits (8O%, 10%, 10%). The process of generating a synthetic dataset can be decomposed into the following steps: |. Prepare styling and content templates: The styling
Every synthetic dataset contains 150k examples, summing
## ances in regard to their size, structure, style and content.
TableFormer: Table Structure Understanding with Transformers Supplementary Material

2
tests/data_scanned/scanned_01.tesserocr.pages.json
View File

File diff suppressed because one or more lines are too long

16
tests/data_scanned/scanned_02.easyocr.doctags.txt
View File

@ -1,7 +1,6 @@
<document> <document>
<figure> <subtitle-level-1><location><page_1><loc_16><loc_87><loc_82><loc_91></location>UNIVERSITYof HOUSTON | CLASS</subtitle-level-1>
<location><page_1><loc_16><loc_87><loc_82><loc_91></location> <subtitle-level-1><location><page_1><loc_30><loc_83><loc_70><loc_86></location>Professional Development Award for Staff</subtitle-level-1>
</figure>
<subtitle-level-1><location><page_1><loc_11><loc_80><loc_20><loc_82></location>Purpose</subtitle-level-1> <subtitle-level-1><location><page_1><loc_11><loc_80><loc_20><loc_82></location>Purpose</subtitle-level-1>
<paragraph><location><page_1><loc_11><loc_69><loc_88><loc_80></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph> <paragraph><location><page_1><loc_11><loc_69><loc_88><loc_80></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_66><loc_21><loc_68></location>Eligibility</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_66><loc_21><loc_68></location>Eligibility</subtitle-level-1>
@ -9,17 +8,14 @@
<subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_63></location>What the Award Will Fund</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_63></location>What the Award Will Fund</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_58><loc_56><loc_61></location>Costs associated with conference/workshop including:</paragraph> <paragraph><location><page_1><loc_12><loc_58><loc_56><loc_61></location>Costs associated with conference/workshop including:</paragraph>
<paragraph><location><page_1><loc_15><loc_57><loc_23><loc_58></location>Airfare</paragraph> <paragraph><location><page_1><loc_15><loc_57><loc_23><loc_58></location>Airfare</paragraph>
<paragraph><location><page_1><loc_15><loc_55><loc_24><loc_56></location>Lodging</paragraph> <paragraph><location><page_1><loc_15><loc_55><loc_24><loc_57></location>Lodging</paragraph>
<paragraph><location><page_1><loc_15><loc_53><loc_23><loc_54></location>Meals</paragraph> <paragraph><location><page_1><loc_15><loc_53><loc_23><loc_55></location>Meals</paragraph>
<paragraph><location><page_1><loc_15><loc_51><loc_32><loc_53></location>Registration fees</paragraph> <paragraph><location><page_1><loc_15><loc_51><loc_32><loc_53></location>Registration fees</paragraph>
<paragraph><location><page_1><loc_15><loc_49><loc_37><loc_51></location>Ground Transportation</paragraph> <paragraph><location><page_1><loc_15><loc_49><loc_37><loc_51></location>Ground Transportation</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_48></location>What the Award Will Not Fund</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_48></location>What the Award Will Not Fund</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_43><loc_78><loc_46></location>expenses incurred outside of the scope of the proposed development activity. Any</paragraph> <paragraph><location><page_1><loc_12><loc_43><loc_78><loc_46></location>expenses incurred outside of the scope of the proposed development activity. Any</paragraph>
<subtitle-level-1><location><page_1><loc_11><loc_40><loc_29><loc_43></location>Granting Schedule</subtitle-level-1> <paragraph><location><page_1><loc_11><loc_40><loc_29><loc_43></location>Granting Schedule</paragraph>
<paragraph><location><page_1><loc_12><loc_38><loc_41><loc_40></location>Earliest Submission Date: August 1st</paragraph> <paragraph><location><page_1><loc_11><loc_34><loc_42><loc_42></location>Earliest Submission Date: August 1st Applications Due: October 1s Notification of Awards: November 1st</paragraph>
<paragraph><location><page_1><loc_11><loc_36><loc_36><loc_38></location>Applications Due: October 1s</paragraph>
<paragraph><location><page_1><loc_11><loc_36><loc_36><loc_38></location>Applications Due: October 1s</paragraph>
<paragraph><location><page_1><loc_12><loc_34><loc_42><loc_36></location>Notification of Awards: November 1st</paragraph>
<paragraph><location><page_1><loc_11><loc_28><loc_85><loc_32></location>Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line.</paragraph> <paragraph><location><page_1><loc_11><loc_28><loc_85><loc_32></location>Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line.</paragraph>
<paragraph><location><page_1><loc_12><loc_19><loc_86><loc_27></location>PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you. will</paragraph> <paragraph><location><page_1><loc_12><loc_19><loc_86><loc_27></location>PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you. will</paragraph>
</document> </document>

2
tests/data_scanned/scanned_02.easyocr.json
View File

File diff suppressed because one or more lines are too long

11
tests/data_scanned/scanned_02.easyocr.md
View File

@ -1,5 +1,6 @@
## UNIVERSITYof HOUSTON | CLASS
<!-- image --> ## Professional Development Award for Staff
## Purpose ## Purpose
@ -27,13 +28,9 @@ Ground Transportation
expenses incurred outside of the scope of the proposed development activity. Any expenses incurred outside of the scope of the proposed development activity. Any
## Granting Schedule Granting Schedule
Earliest Submission Date: August 1st Earliest Submission Date: August 1st Applications Due: October 1s Notification of Awards: November 1st
Applications Due: October 1s
Notification of Awards: November 1st
Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line. Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line.

2
tests/data_scanned/scanned_02.easyocr.pages.json
View File

File diff suppressed because one or more lines are too long

36
tests/data_scanned/scanned_02.tesseract.doctags.txt
View File

@ -1,25 +1,21 @@
<document> <document>
<figure> <subtitle-level-1><location><page_1><loc_16><loc_87><loc_82><loc_91></location>UNIVERSITYof HOUSTON CLASS</subtitle-level-1>
<location><page_1><loc_16><loc_87><loc_82><loc_91></location> <subtitle-level-1><location><page_1><loc_30><loc_84><loc_70><loc_86></location>Professional Development Award for Staff</subtitle-level-1>
</figure> <subtitle-level-1><location><page_1><loc_12><loc_80><loc_20><loc_82></location>Purpose</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_11><loc_80><loc_20><loc_82></location>Purpose</subtitle-level-1> <paragraph><location><page_1><loc_12><loc_69><loc_88><loc_80></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph>
<paragraph><location><page_1><loc_11><loc_69><loc_88><loc_80></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph> <subtitle-level-1><location><page_1><loc_12><loc_66><loc_20><loc_68></location>Eligibility</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_12><loc_66><loc_21><loc_68></location>Eligibility</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_64><loc_51><loc_66></location>All staff currently employed in CLASS are eligible.</paragraph> <paragraph><location><page_1><loc_12><loc_64><loc_51><loc_66></location>All staff currently employed in CLASS are eligible.</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_63></location>What the Award Will Fund</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_63></location>What the Award Will Fund</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_58><loc_56><loc_61></location>Costs associated with conference/workshop including:</paragraph> <paragraph><location><page_1><loc_12><loc_59><loc_56><loc_60></location>Costs associated with conference/workshop including:</paragraph>
<paragraph><location><page_1><loc_15><loc_57><loc_23><loc_58></location>Airfare</paragraph> <paragraph><location><page_1><loc_15><loc_57><loc_23><loc_58></location>e Airfare</paragraph>
<paragraph><location><page_1><loc_15><loc_55><loc_24><loc_56></location>Lodging</paragraph> <paragraph><location><page_1><loc_15><loc_55><loc_24><loc_57></location>e Lodging</paragraph>
<paragraph><location><page_1><loc_15><loc_53><loc_23><loc_54></location>Meals</paragraph> <paragraph><location><page_1><loc_15><loc_53><loc_23><loc_55></location>e Meals</paragraph>
<paragraph><location><page_1><loc_15><loc_51><loc_32><loc_53></location>Registration fees</paragraph> <paragraph><location><page_1><loc_15><loc_51><loc_31><loc_53></location>e Registration fees</paragraph>
<paragraph><location><page_1><loc_15><loc_49><loc_37><loc_51></location>Ground Transportation</paragraph> <paragraph><location><page_1><loc_15><loc_49><loc_36><loc_51></location>e Ground Transportation</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_48></location>What the Award Will Not Fund</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_48></location>What the Award Will Not Fund</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_43><loc_78><loc_46></location>expenses incurred outside of the scope of the proposed development activity. Any</paragraph> <paragraph><location><page_1><loc_12><loc_44><loc_78><loc_45></location>Any expenses incurred outside of the scope of the proposed development activity.</paragraph>
<subtitle-level-1><location><page_1><loc_11><loc_40><loc_29><loc_43></location>Granting Schedule</subtitle-level-1> <subtitle-level-1><location><page_1><loc_12><loc_40><loc_29><loc_42></location>Granting Schedule</subtitle-level-1>
<paragraph><location><page_1><loc_12><loc_38><loc_41><loc_40></location>Earliest Submission Date: August 1st</paragraph> <paragraph><location><page_1><loc_12><loc_34><loc_42><loc_42></location>Granting Schedule Earliest Submission Date: August 1° Applications Due: October 1° Notification of Awards: November 1°</paragraph>
<paragraph><location><page_1><loc_11><loc_36><loc_36><loc_38></location>Applications Due: October 1s</paragraph> <paragraph><location><page_1><loc_12><loc_28><loc_85><loc_32></location>Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional DevelopmentStaff" in the subject line.</paragraph>
<paragraph><location><page_1><loc_11><loc_36><loc_36><loc_38></location>Applications Due: October 1s</paragraph> <paragraph><location><page_1><loc_12><loc_19><loc_86><loc_27></location>PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you.</paragraph>
<paragraph><location><page_1><loc_12><loc_34><loc_42><loc_36></location>Notification of Awards: November 1st</paragraph>
<paragraph><location><page_1><loc_11><loc_28><loc_85><loc_32></location>Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line.</paragraph>
<paragraph><location><page_1><loc_12><loc_19><loc_86><loc_27></location>PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you. will</paragraph>
</document> </document>

2
tests/data_scanned/scanned_02.tesseract.json
View File

File diff suppressed because one or more lines are too long

25
tests/data_scanned/scanned_02.tesseract.md
View File

@ -1,5 +1,6 @@
## UNIVERSITYof HOUSTON CLASS
<!-- image --> ## Professional Development Award for Staff
## Purpose ## Purpose
@ -13,28 +14,24 @@ All staff currently employed in CLASS are eligible.
Costs associated with conference/workshop including: Costs associated with conference/workshop including:
Airfare e Airfare
Lodging e Lodging
Meals e Meals
Registration fees e Registration fees
Ground Transportation e Ground Transportation
## What the Award Will Not Fund ## What the Award Will Not Fund
expenses incurred outside of the scope of the proposed development activity. Any Any expenses incurred outside of the scope of the proposed development activity.
## Granting Schedule ## Granting Schedule
Earliest Submission Date: August 1st Granting Schedule Earliest Submission Date: August 1° Applications Due: October 1° Notification of Awards: November 1°
Applications Due: October 1s Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional DevelopmentStaff" in the subject line.
Notification of Awards: November 1st PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you.
Please submit applications to CLASSGrt@uh edu by the deadline. Please write "Professional Development-Staff" in the subject line.
PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you. will

2
tests/data_scanned/scanned_02.tesseract.pages.json
View File

File diff suppressed because one or more lines are too long

45
tests/data_scanned/scanned_02.tesserocr.doctags.txt
View File

@ -1,27 +1,22 @@
<document> <document>
<figure> <paragraph><location><page_1><loc_12><loc_68><loc_88><loc_81></location>Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional Development- Staff in the subject line. PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you.</paragraph>
<location><page_1><loc_17><loc_87><loc_82><loc_91></location> <paragraph><location><page_1><loc_12><loc_64><loc_51><loc_66></location>Notification of Awards: November 1°"</paragraph>
</figure> <subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_64></location>Applications Due: October 1°</subtitle-level-1>
<subtitle-level-1><location><page_1><loc_12><loc_80><loc_20><loc_82></location>Purpose</subtitle-level-1> <paragraph><location><page_1><loc_12><loc_58><loc_56><loc_60></location>Granting Schedule</paragraph>
<paragraph><location><page_1><loc_12><loc_69><loc_88><loc_80></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph> <paragraph><location><page_1><loc_12><loc_60><loc_41><loc_62></location>Earliest Submission Date: August 1°</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_66><loc_20><loc_68></location>Eligibility</subtitle-level-1> <paragraph><location><page_1><loc_12><loc_55><loc_77><loc_56></location>Any expenses incurred outside of the scope of the proposed development activity.</paragraph>
<paragraph><location><page_1><loc_12><loc_64><loc_51><loc_65></location>All staff currently employed in CLASS are eligible.</paragraph> <paragraph><location><page_1><loc_12><loc_53><loc_41><loc_55></location>What the Awara Will Not Fund</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_61><loc_37><loc_62></location>What the Award Will Fund</subtitle-level-1> <paragraph><location><page_1><loc_15><loc_49><loc_36><loc_51></location>e Ground Transportation</paragraph>
<paragraph><location><page_1><loc_12><loc_59><loc_56><loc_60></location>Costs associated with conference/workshop including:</paragraph> <paragraph><location><page_1><loc_15><loc_48><loc_31><loc_49></location>e Registration fees</paragraph>
<paragraph><location><page_1><loc_15><loc_57><loc_23><loc_58></location>e Airfare</paragraph> <subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_48></location>Meals</subtitle-level-1>
<paragraph><location><page_1><loc_15><loc_55><loc_24><loc_56></location>e Lodging</paragraph> <paragraph><location><page_1><loc_12><loc_44><loc_78><loc_45></location>e Lodging</paragraph>
<paragraph><location><page_1><loc_15><loc_53><loc_23><loc_54></location>e Meals</paragraph> <subtitle-level-1><location><page_1><loc_12><loc_40><loc_29><loc_43></location>e Aijirtare</subtitle-level-1>
<paragraph><location><page_1><loc_15><loc_51><loc_31><loc_52></location>e Registration fees</paragraph> <paragraph><location><page_1><loc_12><loc_34><loc_51><loc_43></location>All staff currently employed in CLASS are eligible. What the Awara Will Fund e Aijirtare</paragraph>
<paragraph><location><page_1><loc_15><loc_49><loc_36><loc_50></location>e Ground Transportation</paragraph> <paragraph><location><page_1><loc_12><loc_40><loc_56><loc_41></location>Costs associated with conference/workshop including:</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_46><loc_41><loc_47></location>What the Award Will Not Fund</subtitle-level-1> <paragraph><location><page_1><loc_12><loc_32><loc_20><loc_34></location>Eligibility</paragraph>
<paragraph><location><page_1><loc_12><loc_44><loc_77><loc_45></location>Any expenses incurred outside of the scope of the proposed development activity.</paragraph> <paragraph><location><page_1><loc_12><loc_28><loc_85><loc_32></location>members that are awarded must wait three years from the date of award notification before reapplying again.</paragraph>
<subtitle-level-1><location><page_1><loc_12><loc_40><loc_29><loc_42></location>Granting Schedule</subtitle-level-1> <paragraph><location><page_1><loc_12><loc_19><loc_88><loc_27></location>The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff</paragraph>
<paragraph><location><page_1><loc_12><loc_39><loc_32><loc_40></location>Earliest Submission Date:</paragraph> <paragraph><location><page_1><loc_12><loc_18><loc_19><loc_20></location>Purpose</paragraph>
<paragraph><location><page_1><loc_33><loc_38><loc_41><loc_40></location>August 1°</paragraph> <paragraph><location><page_1><loc_30><loc_15><loc_70><loc_16></location>Professional Development Award for Staff</paragraph>
<paragraph><location><page_1><loc_12><loc_36><loc_26><loc_38></location>Applications Due:</paragraph> <paragraph><location><page_1><loc_17><loc_9><loc_81><loc_13></location>UNIVERSITYof 'CLASS</paragraph>
<paragraph><location><page_1><loc_27><loc_37><loc_35><loc_38></location>October 1°</paragraph>
<paragraph><location><page_1><loc_12><loc_35><loc_31><loc_36></location>Notification of Awards:</paragraph>
<paragraph><location><page_1><loc_31><loc_35><loc_42><loc_36></location>November 1°</paragraph>
<paragraph><location><page_1><loc_12><loc_28><loc_85><loc_32></location>Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional DevelopmentStaff" in the subject line.</paragraph>
<paragraph><location><page_1><loc_12><loc_19><loc_86><loc_27></location>PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you.</paragraph>
</document> </document>

2
tests/data_scanned/scanned_02.tesserocr.json
View File

File diff suppressed because one or more lines are too long

55
tests/data_scanned/scanned_02.tesserocr.md
View File

@ -1,46 +1,39 @@
Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional Development- Staff in the subject line. PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you.
<!-- image --> Notification of Awards: November 1°"
## Purpose ## Applications Due: October 1°
The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff members that are awarded must wait three years from the date of award notification before reapplying again. Granting Schedule
## Eligibility Earliest Submission Date: August 1°
All staff currently employed in CLASS are eligible.
## What the Award Will Fund
Costs associated with conference/workshop including:
e Airfare
e Lodging
e Meals
e Registration fees
e Ground Transportation
## What the Award Will Not Fund
Any expenses incurred outside of the scope of the proposed development activity. Any expenses incurred outside of the scope of the proposed development activity.
## Granting Schedule What the Awara Will Not Fund
Earliest Submission Date: e Ground Transportation
August 1° e Registration fees
Applications Due: ## Meals
October 1° e Lodging
Notification of Awards: ## e Aijirtare
November 1° All staff currently employed in CLASS are eligible. What the Awara Will Fund e Aijirtare
Please submit applications to CLASSGrt@uh.edu by the deadline. Please write "Professional DevelopmentStaff" in the subject line. Costs associated with conference/workshop including:
PLEASE NOTE: Please include a supporting letter from your Department Chair or Immediate Supervisor. Incomplete applications will not be reviewed. Applications will be considered incomplete until all information has been received, at which time an email confirming receipt will be sent to you. Eligibility
members that are awarded must wait three years from the date of award notification before reapplying again.
The Dean's Professional Development Award for Staff is to allow CLASS staff the opportunity to attend conferences and workshops in their field for the sole purpose of professional development. The intent is to defray costs associated with attendance. The maximum amount of the award is $2,000 per staff member. Up to four awards will be made per year, contingent upon the availability of funding. Staff
Purpose
Professional Development Award for Staff
UNIVERSITYof 'CLASS

2
tests/data_scanned/scanned_02.tesserocr.pages.json
View File

File diff suppressed because one or more lines are too long