Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation

Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively ut...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-05
Hauptverfasser: Varshney, Deeksha, Prabhakar, Akshara, Ekbal, Asif
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Varshney, Deeksha
Prabhakar, Akshara
Ekbal, Asif
description Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark dataset demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at \href{https://github.com/deekshaVarshney/CNTF}{https://github.com/deekshaVarshney/CNTF}; \href{https://www.iitp.ac.in/~ai-nlp-ml/resources/codes/CNTF.zip}{https://www.iitp.ac.in/-ai-nlp-ml/resources/ codes/CNTF.zip}.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2671444548</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2671444548</sourcerecordid><originalsourceid>FETCH-proquest_journals_26714445483</originalsourceid><addsrcrecordid>eNqNjcsKwjAURIMgWLT_EHBdaJNUu5VaHwiu3JdArqWlvVfzoPj3ZuEHCAMH5gzMgiVCyiKrlBArljo35HkudntRljJh15qmidBBDNdo-F1PYHiDvvcffpi1BX5DmkcwHfCzpYAm-mOvR-pCbADBat8TbtjyqUcH6Y9rtj01j_qSvSy9AzjfDhQsRtXG90IpVapK_rf6AmzAPEI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2671444548</pqid></control><display><type>article</type><title>Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation</title><source>Free E- Journals</source><creator>Varshney, Deeksha ; Prabhakar, Akshara ; Ekbal, Asif</creator><creatorcontrib>Varshney, Deeksha ; Prabhakar, Akshara ; Ekbal, Asif</creatorcontrib><description>Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark dataset demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at \href{https://github.com/deekshaVarshney/CNTF}{https://github.com/deekshaVarshney/CNTF}; \href{https://www.iitp.ac.in/~ai-nlp-ml/resources/codes/CNTF.zip}{https://www.iitp.ac.in/-ai-nlp-ml/resources/ codes/CNTF.zip}.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Knowledge ; Modules</subject><ispartof>arXiv.org, 2022-05</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Varshney, Deeksha</creatorcontrib><creatorcontrib>Prabhakar, Akshara</creatorcontrib><creatorcontrib>Ekbal, Asif</creatorcontrib><title>Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation</title><title>arXiv.org</title><description>Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark dataset demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at \href{https://github.com/deekshaVarshney/CNTF}{https://github.com/deekshaVarshney/CNTF}; \href{https://www.iitp.ac.in/~ai-nlp-ml/resources/codes/CNTF.zip}{https://www.iitp.ac.in/-ai-nlp-ml/resources/ codes/CNTF.zip}.</description><subject>Knowledge</subject><subject>Modules</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjcsKwjAURIMgWLT_EHBdaJNUu5VaHwiu3JdArqWlvVfzoPj3ZuEHCAMH5gzMgiVCyiKrlBArljo35HkudntRljJh15qmidBBDNdo-F1PYHiDvvcffpi1BX5DmkcwHfCzpYAm-mOvR-pCbADBat8TbtjyqUcH6Y9rtj01j_qSvSy9AzjfDhQsRtXG90IpVapK_rf6AmzAPEI</recordid><startdate>20220527</startdate><enddate>20220527</enddate><creator>Varshney, Deeksha</creator><creator>Prabhakar, Akshara</creator><creator>Ekbal, Asif</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220527</creationdate><title>Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation</title><author>Varshney, Deeksha ; Prabhakar, Akshara ; Ekbal, Asif</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26714445483</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Knowledge</topic><topic>Modules</topic><toplevel>online_resources</toplevel><creatorcontrib>Varshney, Deeksha</creatorcontrib><creatorcontrib>Prabhakar, Akshara</creatorcontrib><creatorcontrib>Ekbal, Asif</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Varshney, Deeksha</au><au>Prabhakar, Akshara</au><au>Ekbal, Asif</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation</atitle><jtitle>arXiv.org</jtitle><date>2022-05-27</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention layer to preserve the most accurate and critical parts of the dialogue history and the associated knowledge. In addition, we employ a Commonsense and Named Entity Enhanced Attention Module, which starts with the extracted triples from various sources and gradually finds the relevant supporting set of triples using multi-hop attention with the query vector obtained from the interactive dialogue-knowledge module. Empirical results on two benchmark dataset demonstrate that our model significantly outperforms the state-of-the-art methods in terms of both automatic evaluation metrics and human judgment. Our code is publicly available at \href{https://github.com/deekshaVarshney/CNTF}{https://github.com/deekshaVarshney/CNTF}; \href{https://www.iitp.ac.in/~ai-nlp-ml/resources/codes/CNTF.zip}{https://www.iitp.ac.in/-ai-nlp-ml/resources/ codes/CNTF.zip}.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2671444548
source Free E- Journals
subjects Knowledge
Modules
title Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T17%3A04%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Commonsense%20and%20Named%20Entity%20Aware%20Knowledge%20Grounded%20Dialogue%20Generation&rft.jtitle=arXiv.org&rft.au=Varshney,%20Deeksha&rft.date=2022-05-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2671444548%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2671444548&rft_id=info:pmid/&rfr_iscdi=true