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

Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy / Testoni, Alberto; Bernardi, Raffaella. - ELETTRONICO. - (2021), pp. 9330-9338. (Intervento presentato al convegno EMNLP tenutosi a Online and Punta Cana, Dominican Republic nel 7 November 2021) [10.18653/v1/2021.emnlp-main.736].

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

Testoni, Alberto;Bernardi, Raffaella
2021-01-01

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
2021
Proceedings of EMNLP 2021
Online and Punta Cana, Dominican Republic
ACL
Testoni, Alberto; Bernardi, Raffaella
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy / Testoni, Alberto; Bernardi, Raffaella. - ELETTRONICO. - (2021), pp. 9330-9338. (Intervento presentato al convegno EMNLP tenutosi a Online and Punta Cana, Dominican Republic nel 7 November 2021) [10.18653/v1/2021.emnlp-main.736].
File in questo prodotto:
File Dimensione Formato  
2021.emnlp-main.736.pdf

accesso aperto

Descrizione: articolo principale
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 1.52 MB
Formato Adobe PDF
1.52 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/328626
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 1
social impact