Communication Dans Un Congrès Année : 2023

On the inconsistency of separable losses for structured prediction

Caio Corro

Résumé

In this paper, we prove that separable negative log-likelihood losses for structured prediction are not necessarily Bayes consistent, or, in other words, minimizing these losses may not result in a model that predicts the most probable structure in the data distribution for a given input. This fact opens the question of whether these losses are well-adapted for structured prediction and, if so, why.

Fichier principal
Vignette du fichier
2023.eacl-main.109.pdf (315.7 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04394967 , version 1 (15-01-2024)

Licence

Identifiants

Citer

Caio Corro. On the inconsistency of separable losses for structured prediction. 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), May 2023, Dubrovnik, Croatia. pp.1491-1498, ⟨10.18653/v1/2023.eacl-main.109⟩. ⟨hal-04394967⟩
1910 Consultations
208 Téléchargements

Altmetric

Partager

  • More