@inproceedings{chen-etal-2023-tablevlm,
title = "{T}able{VLM}: Multi-modal Pre-training for Table Structure Recognition",
author = "Chen, Leiyuan and
Huang, Chengsong and
Zheng, Xiaoqing and
Lin, Jinshu and
Huang, Xuanjing",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.137",
doi = "10.18653/v1/2023.acl-long.137",
pages = "2437--2449",
abstract = "Tables are widely used in research and business, which are suitable for human consumption, but not easily machine-processable, particularly when tables are present in images. One of the main challenges to extracting data from images of tables is accurately recognizing table structures, especially for complex tables with cross rows and columns. In this study, we propose a novel multi-modal pre-training model for table structure recognition, named TableVLM.With a two-stream multi-modal transformer-based encoder-decoder architecture, TableVLM learns to capture rich table structure-related features by multiple carefully-designed unsupervised objectives inspired by the notion of masked visual-language modeling. To pre-train this model, we also created a dataset, called ComplexTable, which consists of 1,000K samples to be released publicly. Experiment results show that the model built on pre-trained TableVLM can improve the performance up to 1.97{\%} in tree-editing-distance-score on ComplexTable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-tablevlm">
<titleInfo>
<title>TableVLM: Multi-modal Pre-training for Table Structure Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leiyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengsong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinshu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tables are widely used in research and business, which are suitable for human consumption, but not easily machine-processable, particularly when tables are present in images. One of the main challenges to extracting data from images of tables is accurately recognizing table structures, especially for complex tables with cross rows and columns. In this study, we propose a novel multi-modal pre-training model for table structure recognition, named TableVLM.With a two-stream multi-modal transformer-based encoder-decoder architecture, TableVLM learns to capture rich table structure-related features by multiple carefully-designed unsupervised objectives inspired by the notion of masked visual-language modeling. To pre-train this model, we also created a dataset, called ComplexTable, which consists of 1,000K samples to be released publicly. Experiment results show that the model built on pre-trained TableVLM can improve the performance up to 1.97% in tree-editing-distance-score on ComplexTable.</abstract>
<identifier type="citekey">chen-etal-2023-tablevlm</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.137</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.137</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2437</start>
<end>2449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TableVLM: Multi-modal Pre-training for Table Structure Recognition
%A Chen, Leiyuan
%A Huang, Chengsong
%A Zheng, Xiaoqing
%A Lin, Jinshu
%A Huang, Xuanjing
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-tablevlm
%X Tables are widely used in research and business, which are suitable for human consumption, but not easily machine-processable, particularly when tables are present in images. One of the main challenges to extracting data from images of tables is accurately recognizing table structures, especially for complex tables with cross rows and columns. In this study, we propose a novel multi-modal pre-training model for table structure recognition, named TableVLM.With a two-stream multi-modal transformer-based encoder-decoder architecture, TableVLM learns to capture rich table structure-related features by multiple carefully-designed unsupervised objectives inspired by the notion of masked visual-language modeling. To pre-train this model, we also created a dataset, called ComplexTable, which consists of 1,000K samples to be released publicly. Experiment results show that the model built on pre-trained TableVLM can improve the performance up to 1.97% in tree-editing-distance-score on ComplexTable.
%R 10.18653/v1/2023.acl-long.137
%U https://aclanthology.org/2023.acl-long.137
%U https://doi.org/10.18653/v1/2023.acl-long.137
%P 2437-2449
Markdown (Informal)
[TableVLM: Multi-modal Pre-training for Table Structure Recognition](https://aclanthology.org/2023.acl-long.137) (Chen et al., ACL 2023)
ACL
- Leiyuan Chen, Chengsong Huang, Xiaoqing Zheng, Jinshu Lin, and Xuanjing Huang. 2023. TableVLM: Multi-modal Pre-training for Table Structure Recognition. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2437–2449, Toronto, Canada. Association for Computational Linguistics.