Cross-lingual Pronoun Prediction with Linguistically Informed Features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Cross-lingual Pronoun Prediction with Linguistically Informed Features

Résumé

We present the LIMSI's cross-lingual pronoun prediction system for the WMT 2016 shared task. We use high-level linguistic features with explicit coreference resolution and expletive detection and rely on dependency annotations and a morphological lexicon. We show that our few, carefully chosen features perform significantly better than several language model baselines and competitively compared to the other systems submitted.
Fichier principal
Vignette du fichier
wmt16-pronoun-task.pdf (145.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01353862 , version 1 (15-08-2016)

Identifiants

Citer

Rachel Bawden. Cross-lingual Pronoun Prediction with Linguistically Informed Features. First Conference on Machine Translation (WMT '16), Aug 2016, Berlin, Germany. pp.564--570, ⟨10.18653/v1/W16-2348⟩. ⟨hal-01353862⟩
63 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More