Téléchargement | - Voir la version finale : Improved reordering for phrase-based translation using sparse features (PDF, 347 Kio)
|
---|
Lien | https://www.aclweb.org/anthology/N13-1003/ |
---|
Auteur | Rechercher : Cherry, Colin1 |
---|
Affiliation | - Conseil national de recherches du Canada. Technologies de l'information et des communications
|
---|
Format | Texte, Article |
---|
Conférence | 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL, June 9-14, 2013, Atlanta, Georgia |
---|
Résumé | There have been many recent investigations into methods to tune SMT systems using large numbers of sparse features. However, there have not been nearly so many examples of helpful sparse features, especially for phrasebased systems. We use sparse features to address reordering, which is often considered a weak point of phrase-based translation. Using a hierarchical reordering model as our baseline, we show that simple features coupling phrase orientation to frequent words or wordclusters can improve translation quality, with boosts of up to 1.2 BLEU points in Chinese-English and 1.8 in Arabic-English. We compare this solution to a more traditional maximum entropy approach, where a probability model with similar features is trained on wordaligned bitext. We show that sparse decoder features outperform maximum entropy handily, indicating that there are major advantages to optimizing reordering features directly for BLEU with the decoder in the loop. |
---|
Date de publication | 2013-07-01 |
---|
Maison d’édition | ACL |
---|
Licence | |
---|
Dans | |
---|
Langue | anglais |
---|
Publications évaluées par des pairs | Oui |
---|
Numéro NPARC | 21270979 |
---|
Exporter la notice | Exporter en format RIS |
---|
Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
---|
Identificateur de l’enregistrement | bc772d89-6cbc-4c0e-9a8d-06fe29caf286 |
---|
Enregistrement créé | 2014-02-20 |
---|
Enregistrement modifié | 2021-04-26 |
---|