@inproceedings{wu-etal-2022-section,
title = "Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model",
author = "Wu, Sixing and
Li, Ying and
Xue, Ping and
Zhang, Dawei and
Wu, Zhonghai",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.43",
pages = "521--531",
abstract = "In knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. Unlike adopting the plain text knowledge, it is thorny to leverage the structural commonsense knowledge when using PLMs because most PLMs can only operate plain texts. Thus, linearizing commonsense knowledge facts into plan text is a compulsory trick. However, a dialogue is always aligned to a lot of retrieved fact candidates; as a result, the linearized text is always lengthy and then significantly increases the burden of using PLMs. To address this issue, we propose a novel two-stage framework SAKDP. In the first pre-screening stage, we use a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact. Thus, facts can be clustered into three sections of different priorities. As priority decreases, the relevance decreases, and the number of included facts increases. In the next dialogue generation stage, we use section-aware strategies to encode the linearized knowledge. The powerful but expensive PLM is only used for a few facts in the higher priority sections, reaching the performance-efficiency balance. Both the automatic and human evaluation demonstrate the superior performance of this work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-section">
<titleInfo>
<title>Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sixing</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhonghai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. Unlike adopting the plain text knowledge, it is thorny to leverage the structural commonsense knowledge when using PLMs because most PLMs can only operate plain texts. Thus, linearizing commonsense knowledge facts into plan text is a compulsory trick. However, a dialogue is always aligned to a lot of retrieved fact candidates; as a result, the linearized text is always lengthy and then significantly increases the burden of using PLMs. To address this issue, we propose a novel two-stage framework SAKDP. In the first pre-screening stage, we use a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact. Thus, facts can be clustered into three sections of different priorities. As priority decreases, the relevance decreases, and the number of included facts increases. In the next dialogue generation stage, we use section-aware strategies to encode the linearized knowledge. The powerful but expensive PLM is only used for a few facts in the higher priority sections, reaching the performance-efficiency balance. Both the automatic and human evaluation demonstrate the superior performance of this work.</abstract>
<identifier type="citekey">wu-etal-2022-section</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.43</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>521</start>
<end>531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model
%A Wu, Sixing
%A Li, Ying
%A Xue, Ping
%A Zhang, Dawei
%A Wu, Zhonghai
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F wu-etal-2022-section
%X In knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. Unlike adopting the plain text knowledge, it is thorny to leverage the structural commonsense knowledge when using PLMs because most PLMs can only operate plain texts. Thus, linearizing commonsense knowledge facts into plan text is a compulsory trick. However, a dialogue is always aligned to a lot of retrieved fact candidates; as a result, the linearized text is always lengthy and then significantly increases the burden of using PLMs. To address this issue, we propose a novel two-stage framework SAKDP. In the first pre-screening stage, we use a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact. Thus, facts can be clustered into three sections of different priorities. As priority decreases, the relevance decreases, and the number of included facts increases. In the next dialogue generation stage, we use section-aware strategies to encode the linearized knowledge. The powerful but expensive PLM is only used for a few facts in the higher priority sections, reaching the performance-efficiency balance. Both the automatic and human evaluation demonstrate the superior performance of this work.
%U https://aclanthology.org/2022.coling-1.43
%P 521-531
Markdown (Informal)
[Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model](https://aclanthology.org/2022.coling-1.43) (Wu et al., COLING 2022)
ACL