@inproceedings{zhan-etal-2021-augmenting,
title = "Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition",
author = "Zhan, Haolan and
Zhang, Hainan and
Chen, Hongshen and
Ding, Zhuoye and
Bao, Yongjun and
Lan, Yanyan",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.446",
doi = "10.18653/v1/2021.naacl-main.446",
pages = "5621--5630",
abstract = "Knowledge data are massive and widespread in the real-world, which can serve as good external sources to enrich conversations. However, in knowledge-grounded conversations, current models still lack the fine-grained control over knowledge selection and integration with dialogues, which finally leads to the knowledge-irrelevant response generation problems: 1) knowledge selection merely relies on the dialogue context, ignoring the inherent knowledge transitions along with conversation flows; 2) the models often over-fit during training, resulting with incoherent response by referring to unrelated tokens from specific knowledge content in the testing phase; 3) although response is generated upon the dialogue history and knowledge, the models often tend to overlook the selected knowledge, and hence generates knowledge-irrelevant response. To address these problems, we proposed to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags. Besides, to fully utilizing the selected knowledge in generative process, we propose pre-training a knowledge-aware response generator to pay more attention on the selected knowledge. In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data. Experimental results on both structured and unstructured knowledge-grounded dialogue benchmarks indicate that our model achieves better performance over baseline models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhan-etal-2021-augmenting">
<titleInfo>
<title>Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haolan</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hainan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongshen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoye</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjun</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Knowledge data are massive and widespread in the real-world, which can serve as good external sources to enrich conversations. However, in knowledge-grounded conversations, current models still lack the fine-grained control over knowledge selection and integration with dialogues, which finally leads to the knowledge-irrelevant response generation problems: 1) knowledge selection merely relies on the dialogue context, ignoring the inherent knowledge transitions along with conversation flows; 2) the models often over-fit during training, resulting with incoherent response by referring to unrelated tokens from specific knowledge content in the testing phase; 3) although response is generated upon the dialogue history and knowledge, the models often tend to overlook the selected knowledge, and hence generates knowledge-irrelevant response. To address these problems, we proposed to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags. Besides, to fully utilizing the selected knowledge in generative process, we propose pre-training a knowledge-aware response generator to pay more attention on the selected knowledge. In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data. Experimental results on both structured and unstructured knowledge-grounded dialogue benchmarks indicate that our model achieves better performance over baseline models.</abstract>
<identifier type="citekey">zhan-etal-2021-augmenting</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.446</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.446</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5621</start>
<end>5630</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition
%A Zhan, Haolan
%A Zhang, Hainan
%A Chen, Hongshen
%A Ding, Zhuoye
%A Bao, Yongjun
%A Lan, Yanyan
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F zhan-etal-2021-augmenting
%X Knowledge data are massive and widespread in the real-world, which can serve as good external sources to enrich conversations. However, in knowledge-grounded conversations, current models still lack the fine-grained control over knowledge selection and integration with dialogues, which finally leads to the knowledge-irrelevant response generation problems: 1) knowledge selection merely relies on the dialogue context, ignoring the inherent knowledge transitions along with conversation flows; 2) the models often over-fit during training, resulting with incoherent response by referring to unrelated tokens from specific knowledge content in the testing phase; 3) although response is generated upon the dialogue history and knowledge, the models often tend to overlook the selected knowledge, and hence generates knowledge-irrelevant response. To address these problems, we proposed to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags. Besides, to fully utilizing the selected knowledge in generative process, we propose pre-training a knowledge-aware response generator to pay more attention on the selected knowledge. In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data. Experimental results on both structured and unstructured knowledge-grounded dialogue benchmarks indicate that our model achieves better performance over baseline models.
%R 10.18653/v1/2021.naacl-main.446
%U https://aclanthology.org/2021.naacl-main.446
%U https://doi.org/10.18653/v1/2021.naacl-main.446
%P 5621-5630
Markdown (Informal)
[Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition](https://aclanthology.org/2021.naacl-main.446) (Zhan et al., NAACL 2021)
ACL