Toward Stance-based Personas for Opinionated Dialogues

Thomas Scialom, Serra Sinem Tekiroğlu, Jacopo Staiano, Marco Guerini


Abstract
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations. Still, the representation of such personas has thus far been limited to a fact-based representation (e.g. “I have two cats.”). We argue that these representations remain superficial w.r.t. the complexity of human personality. In this work, we propose to make a step forward and investigate stance-based persona, trying to grasp more profound characteristics, such as opinions, values, and beliefs to drive language generation. To this end, we introduce a novel dataset allowing to explore different stance-based persona representations and their impact on claim generation, showing that they are able to grasp abstract and profound aspects of the author persona.
Anthology ID:
2020.findings-emnlp.238
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2625–2635
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.238
DOI:
10.18653/v1/2020.findings-emnlp.238
Bibkey:
Cite (ACL):
Thomas Scialom, Serra Sinem Tekiroğlu, Jacopo Staiano, and Marco Guerini. 2020. Toward Stance-based Personas for Opinionated Dialogues. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2625–2635, Online. Association for Computational Linguistics.
Cite (Informal):
Toward Stance-based Personas for Opinionated Dialogues (Scialom et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.238.pdf
Video:
 https://slideslive.com/38940065