"The red one!": on learning to refer to things based on discriminative properties
"The red one!": on learning to refer to things based on discriminative properties
Citació
- Lazaridou A, The Pham N, Baroni M. "The red one!": on learning to refer to things based on discriminative properties. In: Erk K, Smith NA, editors. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers); 2016 Aug 7-12; Berlin, Germany. Stroudsburg (PA): Association for Computational Linguistics; 2016. p. 213-8. DOI: 10.18653/v1/P16-2035
Enllaç permanent
Descripció
Resum
As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (CAT) and a context (SOFA), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, although supervision is only provided in terms of discriminativeness of attributes for pairs, the model learns to assign plausible attributes to specific objects (SOFA-has_cushion). Finally, we present a preliminary experiment confirming the referential success of the predicted discriminative attributes.Descripció
Comunicació presentada a: 54th Annual Meeting of the Association for Computational Linguistics celebrat del 7 al 12 d'agost de 2016 a Berlín, Alemanya.