@inproceedings{kongyoung-etal-2023-multi,
title = "Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting",
author = "Kongyoung, Sarawoot and
MacDonald, Craig and
Ounis, Iadh",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.913",
doi = "10.18653/v1/2023.findings-emnlp.913",
pages = "13667--13678",
abstract = "In conversational search settings, users ask questions and receive answers as part of a conversation. The ambiguity in the questions is a common challenge, which can be effectively addressed by leveraging contextual information from the conversation history. In this context, determining topic continuity and reformulating questions into well-defined queries are crucial tasks. Previous approaches have typically addressed these tasks either as a classification task in the case of topic continuity or as a text generation task for question reformulation. However, no prior work has combined both tasks to effectively identify ambiguous questions as part of a conversation. In this paper, we propose a Multi-Task Learning (MTL) approach that uses a text generation model for both question rewriting and classification. Our models, based on BART and T5, are trained to rewrite conversational questions and identify follow-up questions simultaneously. We evaluate our approach on multiple test sets and demonstrate that it outperforms single-task learning baselines on the three LIF test sets, with statistically significant improvements ranging from +3.5{\%} to +10.5{\%} in terms of F1 and Micro-F1 scores. We also show that our approach outperforms single-task question rewriting models in passage retrieval on a large OR-QuAC test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kongyoung-etal-2023-multi">
<titleInfo>
<title>Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarawoot</namePart>
<namePart type="family">Kongyoung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">MacDonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iadh</namePart>
<namePart type="family">Ounis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In conversational search settings, users ask questions and receive answers as part of a conversation. The ambiguity in the questions is a common challenge, which can be effectively addressed by leveraging contextual information from the conversation history. In this context, determining topic continuity and reformulating questions into well-defined queries are crucial tasks. Previous approaches have typically addressed these tasks either as a classification task in the case of topic continuity or as a text generation task for question reformulation. However, no prior work has combined both tasks to effectively identify ambiguous questions as part of a conversation. In this paper, we propose a Multi-Task Learning (MTL) approach that uses a text generation model for both question rewriting and classification. Our models, based on BART and T5, are trained to rewrite conversational questions and identify follow-up questions simultaneously. We evaluate our approach on multiple test sets and demonstrate that it outperforms single-task learning baselines on the three LIF test sets, with statistically significant improvements ranging from +3.5% to +10.5% in terms of F1 and Micro-F1 scores. We also show that our approach outperforms single-task question rewriting models in passage retrieval on a large OR-QuAC test set.</abstract>
<identifier type="citekey">kongyoung-etal-2023-multi</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.913</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.913</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13667</start>
<end>13678</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting
%A Kongyoung, Sarawoot
%A MacDonald, Craig
%A Ounis, Iadh
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F kongyoung-etal-2023-multi
%X In conversational search settings, users ask questions and receive answers as part of a conversation. The ambiguity in the questions is a common challenge, which can be effectively addressed by leveraging contextual information from the conversation history. In this context, determining topic continuity and reformulating questions into well-defined queries are crucial tasks. Previous approaches have typically addressed these tasks either as a classification task in the case of topic continuity or as a text generation task for question reformulation. However, no prior work has combined both tasks to effectively identify ambiguous questions as part of a conversation. In this paper, we propose a Multi-Task Learning (MTL) approach that uses a text generation model for both question rewriting and classification. Our models, based on BART and T5, are trained to rewrite conversational questions and identify follow-up questions simultaneously. We evaluate our approach on multiple test sets and demonstrate that it outperforms single-task learning baselines on the three LIF test sets, with statistically significant improvements ranging from +3.5% to +10.5% in terms of F1 and Micro-F1 scores. We also show that our approach outperforms single-task question rewriting models in passage retrieval on a large OR-QuAC test set.
%R 10.18653/v1/2023.findings-emnlp.913
%U https://aclanthology.org/2023.findings-emnlp.913
%U https://doi.org/10.18653/v1/2023.findings-emnlp.913
%P 13667-13678
Markdown (Informal)
[Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting](https://aclanthology.org/2023.findings-emnlp.913) (Kongyoung et al., Findings 2023)
ACL