@inproceedings{ju-etal-2022-learning,
title = "Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement",
author = "Ju, Dongshi and
Feng, Shi and
Lv, Pengcheng and
Wang, Daling and
Zhang, Yifei",
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-1.23",
pages = "298--309",
abstract = "In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human{'}s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ju-etal-2022-learning">
<titleInfo>
<title>Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongshi</namePart>
<namePart type="family">Ju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daling</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Zhang</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>In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.</abstract>
<identifier type="citekey">ju-etal-2022-learning</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.23</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>298</start>
<end>309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement
%A Ju, Dongshi
%A Feng, Shi
%A Lv, Pengcheng
%A Wang, Daling
%A Zhang, Yifei
%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 ju-etal-2022-learning
%X In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues. Existing methods suffer from the incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. Besides, the addressee information, which is closely related to express personality in multi-party dialogues, has been neglected. In this paper, we construct a multi-party personalized dialogue dataset and propose a graph convolution network model (PersonaTKG) with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. Extensive experiments have shown that PersonaTKG outperforms the baselines by large margins and effectively improves persona consistency in the generated responses.
%U https://aclanthology.org/2022.coling-1.23
%P 298-309
Markdown (Informal)
[Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement](https://aclanthology.org/2022.coling-1.23) (Ju et al., COLING 2022)
ACL