@inproceedings{wu-etal-2022-qaconv,
title = "{QAC}onv: Question Answering on Informative Conversations",
author = "Wu, Chien-Sheng and
Madotto, Andrea and
Liu, Wenhao and
Fung, Pascale and
Xiong, Caiming",
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.370",
doi = "10.18653/v1/2022.acl-long.370",
pages = "5389--5411",
abstract = "This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. We focus on informative conversations, including business emails, panel discussions, and work channels. Unlike open-domain and task-oriented dialogues, these conversations are usually long, complex, asynchronous, and involve strong domain knowledge. In total, we collect 34,608 QA pairs from 10,259 selected conversations with both human-written and machine-generated questions. We use a question generator and a dialogue summarizer as auxiliary tools to collect and recommend questions. The dataset has two testing scenarios: chunk mode and full mode, depending on whether the grounded partial conversation is provided or retrieved. Experimental results show that state-of-the-art pretrained QA systems have limited zero-shot performance and tend to predict our questions as unanswerable. Our dataset provides a new training and evaluation testbed to facilitate QA on conversations research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-qaconv">
<titleInfo>
<title>QAConv: Question Answering on Informative Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chien-Sheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</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>This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. We focus on informative conversations, including business emails, panel discussions, and work channels. Unlike open-domain and task-oriented dialogues, these conversations are usually long, complex, asynchronous, and involve strong domain knowledge. In total, we collect 34,608 QA pairs from 10,259 selected conversations with both human-written and machine-generated questions. We use a question generator and a dialogue summarizer as auxiliary tools to collect and recommend questions. The dataset has two testing scenarios: chunk mode and full mode, depending on whether the grounded partial conversation is provided or retrieved. Experimental results show that state-of-the-art pretrained QA systems have limited zero-shot performance and tend to predict our questions as unanswerable. Our dataset provides a new training and evaluation testbed to facilitate QA on conversations research.</abstract>
<identifier type="citekey">wu-etal-2022-qaconv</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.370</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.370</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5389</start>
<end>5411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QAConv: Question Answering on Informative Conversations
%A Wu, Chien-Sheng
%A Madotto, Andrea
%A Liu, Wenhao
%A Fung, Pascale
%A Xiong, Caiming
%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 wu-etal-2022-qaconv
%X This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. We focus on informative conversations, including business emails, panel discussions, and work channels. Unlike open-domain and task-oriented dialogues, these conversations are usually long, complex, asynchronous, and involve strong domain knowledge. In total, we collect 34,608 QA pairs from 10,259 selected conversations with both human-written and machine-generated questions. We use a question generator and a dialogue summarizer as auxiliary tools to collect and recommend questions. The dataset has two testing scenarios: chunk mode and full mode, depending on whether the grounded partial conversation is provided or retrieved. Experimental results show that state-of-the-art pretrained QA systems have limited zero-shot performance and tend to predict our questions as unanswerable. Our dataset provides a new training and evaluation testbed to facilitate QA on conversations research.
%R 10.18653/v1/2022.acl-long.370
%U https://aclanthology.org/2022.acl-long.370
%U https://doi.org/10.18653/v1/2022.acl-long.370
%P 5389-5411
Markdown (Informal)
[QAConv: Question Answering on Informative Conversations](https://aclanthology.org/2022.acl-long.370) (Wu et al., ACL 2022)
ACL
- Chien-Sheng Wu, Andrea Madotto, Wenhao Liu, Pascale Fung, and Caiming Xiong. 2022. QAConv: Question Answering on Informative Conversations. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5389–5411, Dublin, Ireland. Association for Computational Linguistics.