Communication Dans Un Congrès Année : 2007

Combining Morphosyntactic Enriched Representation with n-best Reranking in Statistical Translation

Hélène Bonneau-Maynard
  • Fonction : Auteur
  • PersonId : 177303
  • IdHAL : hbm
  • IdRef : 137151756
Daniel Déchelotte
  • Fonction : Auteur
  • PersonId : 1664296
  • IdRef : 124744362
Holger Schwenk
  • Fonction : Auteur
  • PersonId : 910684
  • IdRef : 12474446X

Résumé

The purpose of this work is to explore the integration of morphosyntactic information into the translation model itself, by enriching words with their morphosyntactic categories. We investigate word disambiguation using morphosyntactic categories, n-best hypotheses reranking, and the combination of both methods with word or morphosyntactic n-gram language model reranking. Experiments are carried out on the English-to-Spanish translation task. Using the morphosyntactic language model alone does not results in any improvement in performance. However, combining morphosyntactic word disambiguation with a word based 4-gram language model results in a relative improvement in the BLEU score of 2.3% on the development set and 1.9% on the test set.

Fichier non déposé

Dates et versions

hal-01434104 , version 1 (13-01-2017)

Identifiants

  • HAL Id : hal-01434104 , version 1

Citer

Hélène Bonneau-Maynard, Alexandre Allauzen, Daniel Déchelotte, Holger Schwenk. Combining Morphosyntactic Enriched Representation with n-best Reranking in Statistical Translation. HLT/NACL workshop on Syntax and Structure in Statistical Translation, Apr 2007, Rochester, United States. pp.65-71. ⟨hal-01434104⟩
147 Consultations
0 Téléchargements

Partager

  • More