Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy

Alberto Testoni, Raffaella Bernardi


Abstract
Generating goal-oriented questions in Visual Dialogue tasks is a challenging and longstanding problem. State-Of-The-Art systems are shown to generate questions that, although grammatically correct, often lack an effective strategy and sound unnatural to humans. Inspired by the cognitive literature on information search and cross-situational word learning, we design Confirm-it, a model based on a beam search re-ranking algorithm that guides an effective goal-oriented strategy by asking questions that confirm the model’s conjecture about the referent. We take the GuessWhat?! game as a case-study. We show that dialogues generated by Confirm-it are more natural and effective than beam search decoding without re-ranking.
Anthology ID:
2021.emnlp-main.736
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9330–9338
Language:
URL:
https://aclanthology.org/2021.emnlp-main.736
DOI:
10.18653/v1/2021.emnlp-main.736
Bibkey:
Cite (ACL):
Alberto Testoni and Raffaella Bernardi. 2021. Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9330–9338, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy (Testoni & Bernardi, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.736.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.736.mp4
Code
 albertotestoni/confirm_it
Data
GuessWhat?!