@inproceedings{song-etal-2021-bob,
title = "{B}o{B}: {BERT} Over {BERT} for Training Persona-based Dialogue Models from Limited Personalized Data",
author = "Song, Haoyu and
Wang, Yan and
Zhang, Kaiyan and
Zhang, Wei-Nan and
Liu, Ting",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.14/",
doi = "10.18653/v1/2021.acl-long.14",
pages = "167--177",
abstract = "Maintaining a consistent persona is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated personalized dialogue datasets is still a barrier towards training robust and consistent persona-based dialogue models. This work shows how this challenge can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2021-bob">
<titleInfo>
<title>BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Nan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Maintaining a consistent persona is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated personalized dialogue datasets is still a barrier towards training robust and consistent persona-based dialogue models. This work shows how this challenge can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency.</abstract>
<identifier type="citekey">song-etal-2021-bob</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.14</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.14/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>167</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
%A Song, Haoyu
%A Wang, Yan
%A Zhang, Kaiyan
%A Zhang, Wei-Nan
%A Liu, Ting
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F song-etal-2021-bob
%X Maintaining a consistent persona is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated personalized dialogue datasets is still a barrier towards training robust and consistent persona-based dialogue models. This work shows how this challenge can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency.
%R 10.18653/v1/2021.acl-long.14
%U https://aclanthology.org/2021.acl-long.14/
%U https://doi.org/10.18653/v1/2021.acl-long.14
%P 167-177
Markdown (Informal)
[BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data](https://aclanthology.org/2021.acl-long.14/) (Song et al., ACL-IJCNLP 2021)
ACL