When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate linguistically richer dialogues, since the acquisition of language proficiency takes longer than learning the guessing task. By comparing models playing different games (GuessWhat, GuessWhich, and Mutual Friends), we show that this discrepancy is model- and task-agnostic. We investigate whether and when better language quality could lead to higher task success. We show that in GuessWhat, models could increase their accuracy if they learn to ground, encode, and decode also words that do not occur frequently in the training set.
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues / Testoni, Alberto; Bernardi, Raffaella. - ELETTRONICO. - (2021), pp. 2071-2082. (Intervento presentato al convegno 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 tenutosi a Online nel 19-23 April 2021) [10.18653/v1/2021.eacl-main.178].
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues
Testoni, Alberto;Bernardi, Raffaella
2021-01-01
Abstract
When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate linguistically richer dialogues, since the acquisition of language proficiency takes longer than learning the guessing task. By comparing models playing different games (GuessWhat, GuessWhich, and Mutual Friends), we show that this discrepancy is model- and task-agnostic. We investigate whether and when better language quality could lead to higher task success. We show that in GuessWhat, models could increase their accuracy if they learn to ground, encode, and decode also words that do not occur frequently in the training set.File | Dimensione | Formato | |
---|---|---|---|
2021.eacl-main.178.pdf
accesso aperto
Descrizione: articolo principale
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
2.29 MB
Formato
Adobe PDF
|
2.29 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione