@inproceedings{shen-etal-2022-knowledge,
title = "Knowledge Enhanced Reflection Generation for Counseling Dialogues",
author = "Shen, Siqi and
Perez-Rosas, Veronica and
Welch, Charles and
Poria, Soujanya and
Mihalcea, Rada",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.221",
doi = "10.18653/v1/2022.acl-long.221",
pages = "3096--3107",
abstract = "In this paper, we study the effect of commonsense and domain knowledge while generating responses in counseling conversations using retrieval and generative methods for knowledge integration. We propose a pipeline that collects domain knowledge through web mining, and show that retrieval from both domain-specific and commonsense knowledge bases improves the quality of generated responses. We also present a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. We show that both retrieved and COMET-generated knowledge improve the system{'}s performance as measured by automatic metrics and also by human evaluation. Lastly, we present a comparative study on the types of knowledge encoded by our system showing that \textit{causal} and \textit{intentional} relationships benefit the generation task more than other types of commonsense relations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2022-knowledge">
<titleInfo>
<title>Knowledge Enhanced Reflection Generation for Counseling Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronica</namePart>
<namePart type="family">Perez-Rosas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Welch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we study the effect of commonsense and domain knowledge while generating responses in counseling conversations using retrieval and generative methods for knowledge integration. We propose a pipeline that collects domain knowledge through web mining, and show that retrieval from both domain-specific and commonsense knowledge bases improves the quality of generated responses. We also present a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. We show that both retrieved and COMET-generated knowledge improve the system’s performance as measured by automatic metrics and also by human evaluation. Lastly, we present a comparative study on the types of knowledge encoded by our system showing that causal and intentional relationships benefit the generation task more than other types of commonsense relations.</abstract>
<identifier type="citekey">shen-etal-2022-knowledge</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.221</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.221</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>3096</start>
<end>3107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Enhanced Reflection Generation for Counseling Dialogues
%A Shen, Siqi
%A Perez-Rosas, Veronica
%A Welch, Charles
%A Poria, Soujanya
%A Mihalcea, Rada
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F shen-etal-2022-knowledge
%X In this paper, we study the effect of commonsense and domain knowledge while generating responses in counseling conversations using retrieval and generative methods for knowledge integration. We propose a pipeline that collects domain knowledge through web mining, and show that retrieval from both domain-specific and commonsense knowledge bases improves the quality of generated responses. We also present a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. We show that both retrieved and COMET-generated knowledge improve the system’s performance as measured by automatic metrics and also by human evaluation. Lastly, we present a comparative study on the types of knowledge encoded by our system showing that causal and intentional relationships benefit the generation task more than other types of commonsense relations.
%R 10.18653/v1/2022.acl-long.221
%U https://aclanthology.org/2022.acl-long.221
%U https://doi.org/10.18653/v1/2022.acl-long.221
%P 3096-3107
Markdown (Informal)
[Knowledge Enhanced Reflection Generation for Counseling Dialogues](https://aclanthology.org/2022.acl-long.221) (Shen et al., ACL 2022)
ACL
- Siqi Shen, Veronica Perez-Rosas, Charles Welch, Soujanya Poria, and Rada Mihalcea. 2022. Knowledge Enhanced Reflection Generation for Counseling Dialogues. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3096–3107, Dublin, Ireland. Association for Computational Linguistics.