@inproceedings{li-etal-2022-mmcoqa,
title = "{MMC}o{QA}: Conversational Question Answering over Text, Tables, and Images",
author = "Li, Yongqi and
Li, Wenjie and
Nie, Liqiang",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.290",
doi = "10.18653/v1/2022.acl-long.290",
pages = "4220--4231",
abstract = "The rapid development of conversational assistants accelerates the study on conversational question answering (QA). However, the existing conversational QA systems usually answer users{'} questions with a single knowledge source, e.g., paragraphs or a knowledge graph, but overlook the important visual cues, let alone multiple knowledge sources of different modalities. In this paper, we hence define a novel research task, i.e., multimodal conversational question answering (MMCoQA), aiming to answer users{'} questions with multimodal knowledge sources via multi-turn conversations. This new task brings a series of research challenges, including but not limited to priority, consistency, and complementarity of multimodal knowledge. To facilitate the data-driven approaches in this area, we construct the first multimodal conversational QA dataset, named MMConvQA. Questions are fully annotated with not only natural language answers but also the corresponding evidence and valuable decontextualized self-contained questions. Meanwhile, we introduce an end-to-end baseline model, which divides this complex research task into question understanding, multi-modal evidence retrieval, and answer extraction. Moreover, we report a set of benchmarking results, and the results indicate that there is ample room for improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-mmcoqa">
<titleInfo>
<title>MMCoQA: Conversational Question Answering over Text, Tables, and Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqiang</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid development of conversational assistants accelerates the study on conversational question answering (QA). However, the existing conversational QA systems usually answer users’ questions with a single knowledge source, e.g., paragraphs or a knowledge graph, but overlook the important visual cues, let alone multiple knowledge sources of different modalities. In this paper, we hence define a novel research task, i.e., multimodal conversational question answering (MMCoQA), aiming to answer users’ questions with multimodal knowledge sources via multi-turn conversations. This new task brings a series of research challenges, including but not limited to priority, consistency, and complementarity of multimodal knowledge. To facilitate the data-driven approaches in this area, we construct the first multimodal conversational QA dataset, named MMConvQA. Questions are fully annotated with not only natural language answers but also the corresponding evidence and valuable decontextualized self-contained questions. Meanwhile, we introduce an end-to-end baseline model, which divides this complex research task into question understanding, multi-modal evidence retrieval, and answer extraction. Moreover, we report a set of benchmarking results, and the results indicate that there is ample room for improvement.</abstract>
<identifier type="citekey">li-etal-2022-mmcoqa</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.290</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.290</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4220</start>
<end>4231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMCoQA: Conversational Question Answering over Text, Tables, and Images
%A Li, Yongqi
%A Li, Wenjie
%A Nie, Liqiang
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F li-etal-2022-mmcoqa
%X The rapid development of conversational assistants accelerates the study on conversational question answering (QA). However, the existing conversational QA systems usually answer users’ questions with a single knowledge source, e.g., paragraphs or a knowledge graph, but overlook the important visual cues, let alone multiple knowledge sources of different modalities. In this paper, we hence define a novel research task, i.e., multimodal conversational question answering (MMCoQA), aiming to answer users’ questions with multimodal knowledge sources via multi-turn conversations. This new task brings a series of research challenges, including but not limited to priority, consistency, and complementarity of multimodal knowledge. To facilitate the data-driven approaches in this area, we construct the first multimodal conversational QA dataset, named MMConvQA. Questions are fully annotated with not only natural language answers but also the corresponding evidence and valuable decontextualized self-contained questions. Meanwhile, we introduce an end-to-end baseline model, which divides this complex research task into question understanding, multi-modal evidence retrieval, and answer extraction. Moreover, we report a set of benchmarking results, and the results indicate that there is ample room for improvement.
%R 10.18653/v1/2022.acl-long.290
%U https://aclanthology.org/2022.acl-long.290
%U https://doi.org/10.18653/v1/2022.acl-long.290
%P 4220-4231
Markdown (Informal)
[MMCoQA: Conversational Question Answering over Text, Tables, and Images](https://aclanthology.org/2022.acl-long.290) (Li et al., ACL 2022)
ACL