Context-Aware Neural Machine Translation Models Analysis And Evaluation Through Attention
Résumé
Model explainability has recently become an active research field.Many works are published supporting or criticizing attention weights as model explanation. In this work we adhere to the former and analyze attention as explanation for Context-Aware Neural Machine Translation (CA-NMT). Since its evaluation often concerns the evaluation of models in resolving discourse phenomena ambiguity, we perform analyses and evaluations over coreference links in a parallel corpus. We propose a human evaluation over heatmaps, strengthened by a quantitative evaluation based on attention weights over coreference links and with different metrics purposely designed for this work. Such metrics provide a more explicit evaluation of the CA-NMT models than evaluations using contrastive test suites.
Mots clés
Résolution de coréférences
Évaluation de la traduction automatique neuronale en contexte
Traduction automatique neuronale Explicabilité Résolution de coréférences Évaluation de la traduction automatique neuronale en contexte Machine Translation Explainability Coreference resolution CA-NMT evaluation
Traduction automatique neuronale
Explicabilité
Domaines
Informatique [cs]| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|