{ "schema_name": "DoclingDocument", "version": "1.5.0", "name": "2305.03393v1-pg9", "origin": { "mimetype": "application/pdf", "binary_hash": 3463920545297462180, "filename": "2305.03393v1-pg9.pdf" }, "furniture": { "self_ref": "#/furniture", "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified" }, "body": { "self_ref": "#/body", "children": [ { "$ref": "#/texts/0" }, { "$ref": "#/texts/1" }, { "$ref": "#/texts/2" }, { "$ref": "#/texts/3" }, { "$ref": "#/texts/4" }, { "$ref": "#/tables/0" }, { "$ref": "#/texts/6" }, { "$ref": "#/texts/7" }, { "$ref": "#/texts/8" } ], "content_layer": "body", "name": "_root_", "label": "unspecified" }, "groups": [], "texts": [ { "self_ref": "#/texts/0", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "furniture", "label": "page_header", "prov": [ { "page_no": 1, "bbox": { "l": 194.5, "t": 700.5, "r": 447.5, "b": 689.2, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 60 ] } ], "orig": "Optimized Table Tokenization for Table Structure Recognition", "text": "Optimized Table Tokenization for Table Structure Recognition" }, { "self_ref": "#/texts/1", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "furniture", "label": "page_header", "prov": [ { "page_no": 1, "bbox": { "l": 476.0, "t": 700.5, "r": 480.6, "b": 689.2, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 1 ] } ], "orig": "9", "text": "9" }, { "self_ref": "#/texts/2", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "text", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 675.5, "r": 480.6, "b": 639.1, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 163 ] } ], "orig": "order to compute the TED score. Inference timing results for all experiments were obtained from the same machine on a single core with AMD EPYC 7763 CPU @2.45 GHz.", "text": "order to compute the TED score. Inference timing results for all experiments were obtained from the same machine on a single core with AMD EPYC 7763 CPU @2.45 GHz." }, { "self_ref": "#/texts/3", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "section_header", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 625.3, "r": 318.5, "b": 612.8, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 32 ] } ], "orig": "5.1 Hyper Parameter Optimization", "text": "5.1 Hyper Parameter Optimization", "level": 1 }, { "self_ref": "#/texts/4", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "text", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 608.9, "r": 480.6, "b": 536.6, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 423 ] } ], "orig": "We have chosen the PubTabNet data set to perform HPO, since it includes a highly diverse set of tables. Also we report TED scores separately for simple and complex tables (tables with cell spans). Results are presented in Table. 1. It is evident that with OTSL, our model achieves the same TED score and slightly better mAP scores in comparison to HTML. However OTSL yields a 2x speed up in the inference runtime over HTML.", "text": "We have chosen the PubTabNet data set to perform HPO, since it includes a highly diverse set of tables. Also we report TED scores separately for simple and complex tables (tables with cell spans). Results are presented in Table. 1. It is evident that with OTSL, our model achieves the same TED score and slightly better mAP scores in comparison to HTML. However OTSL yields a 2x speed up in the inference runtime over HTML." }, { "self_ref": "#/texts/5", "parent": { "$ref": "#/tables/0" }, "children": [], "content_layer": "body", "label": "caption", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 519.2, "r": 480.6, "b": 464.0, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 398 ] } ], "orig": "Table 1. HPO performed in OTSL and HTML representation on the same transformer-based TableFormer [9] architecture, trained only on PubTabNet [22]. Effects of reducing the # of layers in encoder and decoder stages of the model show that smaller models trained on OTSL perform better, especially in recognizing complex table structures, and maintain a much higher mAP score than the HTML counterpart.", "text": "Table 1. HPO performed in OTSL and HTML representation on the same transformer-based TableFormer [9] architecture, trained only on PubTabNet [22]. Effects of reducing the # of layers in encoder and decoder stages of the model show that smaller models trained on OTSL perform better, especially in recognizing complex table structures, and maintain a much higher mAP score than the HTML counterpart." }, { "self_ref": "#/texts/6", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "section_header", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 286.3, "r": 264.4, "b": 273.8, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 24 ] } ], "orig": "5.2 Quantitative Results", "text": "5.2 Quantitative Results", "level": 1 }, { "self_ref": "#/texts/7", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "text", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 269.9, "r": 480.7, "b": 173.7, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 555 ] } ], "orig": "We picked the model parameter configuration that produced the best prediction quality (enc=6, dec=6, heads=8) with PubTabNet alone, then independently trained and evaluated it on three publicly available data sets: PubTabNet (395k samples), FinTabNet (113k samples) and PubTables-1M (about 1M samples). Performance results are presented in Table. 2. It is clearly evident that the model trained on OTSL outperforms HTML across the board, keeping high TEDs and mAP scores even on difficult financial tables (FinTabNet) that contain sparse and large tables.", "text": "We picked the model parameter configuration that produced the best prediction quality (enc=6, dec=6, heads=8) with PubTabNet alone, then independently trained and evaluated it on three publicly available data sets: PubTabNet (395k samples), FinTabNet (113k samples) and PubTables-1M (about 1M samples). Performance results are presented in Table. 2. It is clearly evident that the model trained on OTSL outperforms HTML across the board, keeping high TEDs and mAP scores even on difficult financial tables (FinTabNet) that contain sparse and large tables." }, { "self_ref": "#/texts/8", "parent": { "$ref": "#/body" }, "children": [], "content_layer": "body", "label": "text", "prov": [ { "page_no": 1, "bbox": { "l": 134.8, "t": 174.3, "r": 480.6, "b": 125.9, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 289 ] } ], "orig": "Additionally, the results show that OTSL has an advantage over HTML when applied on a bigger data set like PubTables-1M and achieves significantly improved scores. Finally, OTSL achieves faster inference due to fewer decoding steps which is a result of the reduced sequence representation.", "text": "Additionally, the results show that OTSL has an advantage over HTML when applied on a bigger data set like PubTables-1M and achieves significantly improved scores. Finally, OTSL achieves faster inference due to fewer decoding steps which is a result of the reduced sequence representation." } ], "pictures": [], "tables": [ { "self_ref": "#/tables/0", "parent": { "$ref": "#/body" }, "children": [ { "$ref": "#/texts/5" } ], "content_layer": "body", "label": "table", "prov": [ { "page_no": 1, "bbox": { "l": 139.7, "t": 454.5, "r": 475.0, "b": 322.5, "coord_origin": "BOTTOMLEFT" }, "charspan": [ 0, 0 ] } ], "captions": [ { "$ref": "#/texts/5" } ], "references": [], "footnotes": [], "data": { "table_cells": [ { "bbox": { "l": 160.4, "t": 339.5, "r": 168.0, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "# enc-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 208.0, "t": 339.5, "r": 215.6, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "# dec-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 239.8, "t": 344.9, "r": 278.3, "b": 356.2, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "Language", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 324.7, "t": 339.5, "r": 348.3, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 3, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 3, "end_col_offset_idx": 6, "text": "TEDs", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 396.3, "t": 339.5, "r": 417.1, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "mAP", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 394.9, "t": 350.4, "r": 418.5, "b": 361.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "(0.75)", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 430.8, "t": 339.5, "r": 467.1, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "Inference", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 427.1, "t": 350.4, "r": 470.8, "b": 361.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "time (secs)", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 286.7, "t": 352.4, "r": 312.3, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "simple", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 320.7, "t": 352.4, "r": 353.7, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "complex", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 369.3, "t": 352.4, "r": 379.0, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "all", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 161.9, "t": 371.2, "r": 166.5, "b": 382.5, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "6", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 371.2, "r": 214.1, "b": 382.5, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "6", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 365.8, "r": 271.4, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 365.8, "r": 310.0, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.965 0.969", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 365.8, "r": 347.7, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.934 0.927", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 365.8, "r": 384.7, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.955 0.955", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 397.3, "t": 365.7, "r": 416.1, "b": 377.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.88 0.857", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 365.7, "r": 458.4, "b": 377.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "2.73 5.39", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 161.9, "t": 397.5, "r": 166.5, "b": 408.8, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 397.5, "r": 214.1, "b": 408.8, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 392.1, "r": 271.4, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 392.1, "r": 310.0, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.938 0.952", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 392.1, "r": 347.7, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.904 0.909", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 392.1, "r": 384.7, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.927 0.938", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 392.0, "r": 418.8, "b": 403.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.853 0.843", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 392.0, "r": 458.4, "b": 403.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.97 3.77", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 161.9, "t": 423.8, "r": 166.5, "b": 435.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "2", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 423.8, "r": 214.1, "b": 435.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 418.4, "r": 271.4, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 418.4, "r": 310.0, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.923 0.945", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 418.4, "r": 347.7, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.897 0.901", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 418.4, "r": 384.7, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.915 0.931", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 418.3, "r": 418.8, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.859 0.834", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 418.3, "r": 458.4, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.91 3.81", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 161.9, "t": 450.1, "r": 166.5, "b": 461.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 450.1, "r": 214.1, "b": 461.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "2", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 444.7, "r": 271.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 444.7, "r": 310.0, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.952 0.944", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 329.0, "t": 444.7, "r": 345.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.92 0.903", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 362.1, "t": 444.6, "r": 386.2, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.942 0.931", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 444.6, "r": 418.8, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.857 0.824", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 444.6, "r": 458.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.22 2", "column_header": false, "row_header": false, "row_section": false } ], "num_rows": 6, "num_cols": 8, "grid": [ [ { "bbox": { "l": 160.4, "t": 339.5, "r": 168.0, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "# enc-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 208.0, "t": 339.5, "r": 215.6, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "# dec-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 239.8, "t": 344.9, "r": 278.3, "b": 356.2, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "Language", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 324.7, "t": 339.5, "r": 348.3, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 3, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 3, "end_col_offset_idx": 6, "text": "TEDs", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 324.7, "t": 339.5, "r": 348.3, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 3, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 3, "end_col_offset_idx": 6, "text": "TEDs", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 324.7, "t": 339.5, "r": 348.3, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 3, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 3, "end_col_offset_idx": 6, "text": "TEDs", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 396.3, "t": 339.5, "r": 417.1, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "mAP", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 430.8, "t": 339.5, "r": 467.1, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 1, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "Inference", "column_header": true, "row_header": false, "row_section": false } ], [ { "bbox": { "l": 160.4, "t": 339.5, "r": 168.0, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "# enc-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 208.0, "t": 339.5, "r": 215.6, "b": 350.7, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "# dec-layers", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 239.8, "t": 344.9, "r": 278.3, "b": 356.2, "coord_origin": "TOPLEFT" }, "row_span": 2, "col_span": 1, "start_row_offset_idx": 0, "end_row_offset_idx": 2, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "Language", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 286.7, "t": 352.4, "r": 312.3, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "simple", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 320.7, "t": 352.4, "r": 353.7, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "complex", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 369.3, "t": 352.4, "r": 379.0, "b": 363.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "all", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 394.9, "t": 350.4, "r": 418.5, "b": 361.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "(0.75)", "column_header": true, "row_header": false, "row_section": false }, { "bbox": { "l": 427.1, "t": 350.4, "r": 470.8, "b": 361.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 1, "end_row_offset_idx": 2, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "time (secs)", "column_header": true, "row_header": false, "row_section": false } ], [ { "bbox": { "l": 161.9, "t": 371.2, "r": 166.5, "b": 382.5, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "6", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 371.2, "r": 214.1, "b": 382.5, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "6", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 365.8, "r": 271.4, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 365.8, "r": 310.0, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.965 0.969", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 365.8, "r": 347.7, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.934 0.927", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 365.8, "r": 384.7, "b": 377.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.955 0.955", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 397.3, "t": 365.7, "r": 416.1, "b": 377.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.88 0.857", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 365.7, "r": 458.4, "b": 377.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 2, "end_row_offset_idx": 3, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "2.73 5.39", "column_header": false, "row_header": false, "row_section": false } ], [ { "bbox": { "l": 161.9, "t": 397.5, "r": 166.5, "b": 408.8, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 397.5, "r": 214.1, "b": 408.8, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 392.1, "r": 271.4, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 392.1, "r": 310.0, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.938 0.952", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 392.1, "r": 347.7, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.904 0.909", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 392.1, "r": 384.7, "b": 403.3, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.927 0.938", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 392.0, "r": 418.8, "b": 403.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.853 0.843", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 392.0, "r": 458.4, "b": 403.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 3, "end_row_offset_idx": 4, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.97 3.77", "column_header": false, "row_header": false, "row_section": false } ], [ { "bbox": { "l": 161.9, "t": 423.8, "r": 166.5, "b": 435.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "2", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 423.8, "r": 214.1, "b": 435.1, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 418.4, "r": 271.4, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 418.4, "r": 310.0, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.923 0.945", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 326.7, "t": 418.4, "r": 347.7, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.897 0.901", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 363.7, "t": 418.4, "r": 384.7, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.915 0.931", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 418.3, "r": 418.8, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.859 0.834", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 418.3, "r": 458.4, "b": 429.7, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 4, "end_row_offset_idx": 5, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.91 3.81", "column_header": false, "row_header": false, "row_section": false } ], [ { "bbox": { "l": 161.9, "t": 450.1, "r": 166.5, "b": 461.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 0, "end_col_offset_idx": 1, "text": "4", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 209.5, "t": 450.1, "r": 214.1, "b": 461.4, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 1, "end_col_offset_idx": 2, "text": "2", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 246.7, "t": 444.7, "r": 271.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 2, "end_col_offset_idx": 3, "text": "OTSL HTML", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 289.0, "t": 444.7, "r": 310.0, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 3, "end_col_offset_idx": 4, "text": "0.952 0.944", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 329.0, "t": 444.7, "r": 345.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 4, "end_col_offset_idx": 5, "text": "0.92 0.903", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 362.1, "t": 444.6, "r": 386.2, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 5, "end_col_offset_idx": 6, "text": "0.942 0.931", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 394.6, "t": 444.6, "r": 418.8, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 6, "end_col_offset_idx": 7, "text": "0.857 0.824", "column_header": false, "row_header": false, "row_section": false }, { "bbox": { "l": 439.5, "t": 444.6, "r": 458.4, "b": 456.0, "coord_origin": "TOPLEFT" }, "row_span": 1, "col_span": 1, "start_row_offset_idx": 5, "end_row_offset_idx": 6, "start_col_offset_idx": 7, "end_col_offset_idx": 8, "text": "1.22 2", "column_header": false, "row_header": false, "row_section": false } ] ] }, "annotations": [] } ], "key_value_items": [], "form_items": [], "pages": { "1": { "size": { "width": 612.0, "height": 792.0 }, "page_no": 1 } } }