Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020
DOI: 10.18653/v1/2020.acl-main.7
|View full text |Cite
|
Sign up to set email alerts
|

Guiding Variational Response Generator to Exploit Persona

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 ad… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
18
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 29 publications
(24 citation statements)
references
References 30 publications
0
18
0
Order By: Relevance
“…Personalized dialogue generation [66] is one of the most active research topics in personalized text generation, which aims at generating persona-aware responses in multi-turn conversation. They mainly focus on exploiting the prerequisite personal textual information to control the persona-consistency [53,60] and enhance the diversity in response generation [54,59]. Another widely-studied area is personalized review generation [35,46,55] and summarization [34,37].…”
Section: Personalized Text Generationmentioning
confidence: 99%
“…Personalized dialogue generation [66] is one of the most active research topics in personalized text generation, which aims at generating persona-aware responses in multi-turn conversation. They mainly focus on exploiting the prerequisite personal textual information to control the persona-consistency [53,60] and enhance the diversity in response generation [54,59]. Another widely-studied area is personalized review generation [35,46,55] and summarization [34,37].…”
Section: Personalized Text Generationmentioning
confidence: 99%
“…Speaker Identification (SI). As explored in (Bak and Oh, 2019;Wu et al, 2020;Liang et al, 2021b;Lin et al, 2021), the history utterances of a speaker can reflect a distinctive personality. 11…”
Section: Speaker Personality Modelingmentioning
confidence: 99%
“…Correspondingly, some "nearby" speakers might have similar words. Similar to Li et al (2016b), Wu et al (2020) used similar input information while using a different variational generation approach to generate diverse responses. They used two regularization terms to guide the model to pay more attention to the user's hidden information and language preference.…”
Section: Related Workmentioning
confidence: 99%
“…To address the interestingness and response diversity issues, some studies have focused on improving the style or response characteristics to resemble human-produced ones. One approach is to integrate user-specific information/features (Li et al 2016b;Bak and Oh 2019;Wu et al 2020), or some specific persona characteristics (Chu et al 2018;Li et al 2020) to establish the association between the responses and the corresponding persona. Another approach is to transfer the specific style or latent information from additional texts to the responses (Herzig et al 2017;Zhang et al 2018;Gao et al 2019).…”
mentioning
confidence: 99%