@inproceedings{tang-etal-2024-multiple,
title = "Multiple-Question Multiple-Answer Text-{VQA}",
author = "Tang, Peng and
Appalaraju, Srikar and
Manmatha, R. and
Xie, Yusheng and
Mahadevan, Vijay",
editor = "Yang, Yi and
Davani, Aida and
Sil, Avi and
Kumar, Anoop",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-industry.7",
doi = "10.18653/v1/2024.naacl-industry.7",
pages = "73--88",
abstract = "We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. To the best of our knowledge, almost all previous approaches for text-VQA process a single question and its associated content to predict a single answer. However, in industry applications, users may come up with multiple questions about a single image. In order to answer multiple questions from the same image, each question and content are fed into the model multiple times. In contrast, our proposed MQMA approach takes multiple questions and content as input at the encoder and predicts multiple answers at the decoder in an auto-regressive manner at the same time. We make several novel architectural modifications to standard encoder-decoder transformers to support MQMA. We also propose a novel MQMA denoising pre-training task which is designed to teach the model to align and delineate multiple questions and content with associated answers. MQMA pre-trained model achieves state-of-the-art results on multiple text-VQA datasets, each with strong baselines. Specifically, on OCR-VQA (+2.5{\%}), TextVQA (+1.4{\%}), ST-VQA (+0.6{\%}), DocVQA (+1.1{\%}) absolute improvements over the previous state-of-the-art approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2024-multiple">
<titleInfo>
<title>Multiple-Question Multiple-Answer Text-VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srikar</namePart>
<namePart type="family">Appalaraju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">R</namePart>
<namePart type="family">Manmatha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusheng</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="family">Mahadevan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. To the best of our knowledge, almost all previous approaches for text-VQA process a single question and its associated content to predict a single answer. However, in industry applications, users may come up with multiple questions about a single image. In order to answer multiple questions from the same image, each question and content are fed into the model multiple times. In contrast, our proposed MQMA approach takes multiple questions and content as input at the encoder and predicts multiple answers at the decoder in an auto-regressive manner at the same time. We make several novel architectural modifications to standard encoder-decoder transformers to support MQMA. We also propose a novel MQMA denoising pre-training task which is designed to teach the model to align and delineate multiple questions and content with associated answers. MQMA pre-trained model achieves state-of-the-art results on multiple text-VQA datasets, each with strong baselines. Specifically, on OCR-VQA (+2.5%), TextVQA (+1.4%), ST-VQA (+0.6%), DocVQA (+1.1%) absolute improvements over the previous state-of-the-art approaches.</abstract>
<identifier type="citekey">tang-etal-2024-multiple</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-industry.7</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-industry.7</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>73</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiple-Question Multiple-Answer Text-VQA
%A Tang, Peng
%A Appalaraju, Srikar
%A Manmatha, R.
%A Xie, Yusheng
%A Mahadevan, Vijay
%Y Yang, Yi
%Y Davani, Aida
%Y Sil, Avi
%Y Kumar, Anoop
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F tang-etal-2024-multiple
%X We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. To the best of our knowledge, almost all previous approaches for text-VQA process a single question and its associated content to predict a single answer. However, in industry applications, users may come up with multiple questions about a single image. In order to answer multiple questions from the same image, each question and content are fed into the model multiple times. In contrast, our proposed MQMA approach takes multiple questions and content as input at the encoder and predicts multiple answers at the decoder in an auto-regressive manner at the same time. We make several novel architectural modifications to standard encoder-decoder transformers to support MQMA. We also propose a novel MQMA denoising pre-training task which is designed to teach the model to align and delineate multiple questions and content with associated answers. MQMA pre-trained model achieves state-of-the-art results on multiple text-VQA datasets, each with strong baselines. Specifically, on OCR-VQA (+2.5%), TextVQA (+1.4%), ST-VQA (+0.6%), DocVQA (+1.1%) absolute improvements over the previous state-of-the-art approaches.
%R 10.18653/v1/2024.naacl-industry.7
%U https://aclanthology.org/2024.naacl-industry.7
%U https://doi.org/10.18653/v1/2024.naacl-industry.7
%P 73-88
Markdown (Informal)
[Multiple-Question Multiple-Answer Text-VQA](https://aclanthology.org/2024.naacl-industry.7) (Tang et al., NAACL 2024)
ACL
- Peng Tang, Srikar Appalaraju, R. Manmatha, Yusheng Xie, and Vijay Mahadevan. 2024. Multiple-Question Multiple-Answer Text-VQA. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pages 73–88, Mexico City, Mexico. Association for Computational Linguistics.