@inproceedings{yang-etal-2022-take,
title = "{TAKE}: Topic-shift Aware Knowledge s{E}lection for Dialogue Generation",
author = "Yang, Chenxu and
Lin, Zheng and
Li, Jiangnan and
Meng, Fandong and
Wang, Weiping and
Wang, Lanrui and
Zhou, Jie",
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-1.20",
pages = "253--265",
abstract = "Knowledge-grounded dialogue generation consists of two subtasks: knowledge selection and response generation. The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation. Recent work finds that realizing who (the user or the agent) holds the initiative and utilizing the role-initiative information to instruct the query construction can help select knowledge. It depends on whether the knowledge connection between two adjacent rounds is smooth to assign the role. However, whereby the user takes the initiative only when there is a strong semantic transition between two rounds, probably leading to initiative misjudgment. Therefore, it is necessary to seek a more sensitive reason beyond the initiative role for knowledge selection. To address the above problem, we propose a Topic-shift Aware Knowledge sElector(TAKE). Specifically, we first annotate the topic shift and topic inheritance labels in multi-round dialogues with distant supervision. Then, we alleviate the noise problem in pseudo labels through curriculum learning and knowledge distillation. Extensive experiments on WoW show that TAKE performs better than strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2022-take">
<titleInfo>
<title>TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenxu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangnan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fandong</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiping</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lanrui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</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>
<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>Knowledge-grounded dialogue generation consists of two subtasks: knowledge selection and response generation. The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation. Recent work finds that realizing who (the user or the agent) holds the initiative and utilizing the role-initiative information to instruct the query construction can help select knowledge. It depends on whether the knowledge connection between two adjacent rounds is smooth to assign the role. However, whereby the user takes the initiative only when there is a strong semantic transition between two rounds, probably leading to initiative misjudgment. Therefore, it is necessary to seek a more sensitive reason beyond the initiative role for knowledge selection. To address the above problem, we propose a Topic-shift Aware Knowledge sElector(TAKE). Specifically, we first annotate the topic shift and topic inheritance labels in multi-round dialogues with distant supervision. Then, we alleviate the noise problem in pseudo labels through curriculum learning and knowledge distillation. Extensive experiments on WoW show that TAKE performs better than strong baselines.</abstract>
<identifier type="citekey">yang-etal-2022-take</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.20</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>253</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation
%A Yang, Chenxu
%A Lin, Zheng
%A Li, Jiangnan
%A Meng, Fandong
%A Wang, Weiping
%A Wang, Lanrui
%A Zhou, Jie
%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 yang-etal-2022-take
%X Knowledge-grounded dialogue generation consists of two subtasks: knowledge selection and response generation. The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation. Recent work finds that realizing who (the user or the agent) holds the initiative and utilizing the role-initiative information to instruct the query construction can help select knowledge. It depends on whether the knowledge connection between two adjacent rounds is smooth to assign the role. However, whereby the user takes the initiative only when there is a strong semantic transition between two rounds, probably leading to initiative misjudgment. Therefore, it is necessary to seek a more sensitive reason beyond the initiative role for knowledge selection. To address the above problem, we propose a Topic-shift Aware Knowledge sElector(TAKE). Specifically, we first annotate the topic shift and topic inheritance labels in multi-round dialogues with distant supervision. Then, we alleviate the noise problem in pseudo labels through curriculum learning and knowledge distillation. Extensive experiments on WoW show that TAKE performs better than strong baselines.
%U https://aclanthology.org/2022.coling-1.20
%P 253-265
Markdown (Informal)
[TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation](https://aclanthology.org/2022.coling-1.20) (Yang et al., COLING 2022)
ACL
- Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, and Jie Zhou. 2022. TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 253–265, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.