@inproceedings{gu-etal-2021-chaincqg,
title = "{C}hain{CQG}: Flow-Aware Conversational Question Generation",
author = "Gu, Jing and
Mirshekari, Mostafa and
Yu, Zhou and
Sisto, Aaron",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.177",
doi = "10.18653/v1/2021.eacl-main.177",
pages = "2061--2070",
abstract = "Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy. ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48{\%} BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2021-chaincqg">
<titleInfo>
<title>ChainCQG: Flow-Aware Conversational Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Mirshekari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Sisto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy. ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48% BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.</abstract>
<identifier type="citekey">gu-etal-2021-chaincqg</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.177</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.177</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>2061</start>
<end>2070</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChainCQG: Flow-Aware Conversational Question Generation
%A Gu, Jing
%A Mirshekari, Mostafa
%A Yu, Zhou
%A Sisto, Aaron
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F gu-etal-2021-chaincqg
%X Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy. ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48% BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.
%R 10.18653/v1/2021.eacl-main.177
%U https://aclanthology.org/2021.eacl-main.177
%U https://doi.org/10.18653/v1/2021.eacl-main.177
%P 2061-2070
Markdown (Informal)
[ChainCQG: Flow-Aware Conversational Question Generation](https://aclanthology.org/2021.eacl-main.177) (Gu et al., EACL 2021)
ACL
- Jing Gu, Mostafa Mirshekari, Zhou Yu, and Aaron Sisto. 2021. ChainCQG: Flow-Aware Conversational Question Generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2061–2070, Online. Association for Computational Linguistics.