Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results.
Bowen Wu, MengYuan Li, Zongsheng Wang, Yifu Chen, Derek F. Wong, Qihang Feng, Junhong Huang, and Baoxun Wang. 2020.Guiding Variational Response Generator to Exploit Persona. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 53–65, Online. Association for Computational Linguistics.
@inproceedings{wu-etal-2020-guiding, title = "Guiding Variational Response Generator to Exploit Persona", author = "Wu, Bowen and Li, MengYuan and Wang, Zongsheng and Chen, Yifu and Wong, Derek F. and Feng, Qihang and Huang, Junhong and Wang, Baoxun", editor = "Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel", booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.acl-main.7/", doi = "10.18653/v1/2020.acl-main.7", pages = "53--65", abstract = "Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="wu-etal-2020-guiding"> <titleInfo> <title>Guiding Variational Response Generator to Exploit Persona</title> </titleInfo> <name type="personal"> <namePart type="given">Bowen</namePart> <namePart type="family">Wu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">MengYuan</namePart> <namePart type="family">Li</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Zongsheng</namePart> <namePart type="family">Wang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yifu</namePart> <namePart type="family">Chen</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Derek</namePart> <namePart type="given">F</namePart> <namePart type="family">Wong</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Qihang</namePart> <namePart type="family">Feng</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Junhong</namePart> <namePart type="family">Huang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Baoxun</namePart> <namePart type="family">Wang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2020-07</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Dan</namePart> <namePart type="family">Jurafsky</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Joyce</namePart> <namePart type="family">Chai</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Natalie</namePart> <namePart type="family">Schluter</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Joel</namePart> <namePart type="family">Tetreault</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>Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results.</abstract> <identifier type="citekey">wu-etal-2020-guiding</identifier> <identifier type="doi">10.18653/v1/2020.acl-main.7</identifier> <location> <url>https://aclanthology.org/2020.acl-main.7/</url> </location> <part> <date>2020-07</date> <extent unit="page"> <start>53</start> <end>65</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Guiding Variational Response Generator to Exploit Persona%A Wu, Bowen%A Li, MengYuan%A Wang, Zongsheng%A Chen, Yifu%A Wong, Derek F.%A Feng, Qihang%A Huang, Junhong%A Wang, Baoxun%Y Jurafsky, Dan%Y Chai, Joyce%Y Schluter, Natalie%Y Tetreault, Joel%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics%D 2020%8 July%I Association for Computational Linguistics%C Online%F wu-etal-2020-guiding%X Leveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years. Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by designing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses. Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental results have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the results.%R 10.18653/v1/2020.acl-main.7%U https://aclanthology.org/2020.acl-main.7/%U https://doi.org/10.18653/v1/2020.acl-main.7%P 53-65
Bowen Wu, MengYuan Li, Zongsheng Wang, Yifu Chen, Derek F. Wong, Qihang Feng, Junhong Huang, and Baoxun Wang. 2020.Guiding Variational Response Generator to Exploit Persona. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 53–65, Online. Association for Computational Linguistics.