Revisiting sentence alignment algorithms for alignment visualization and evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Revisiting sentence alignment algorithms for alignment visualization and evaluation

Résumé

In this paper, we revisit the well-known problem of sentence alignment, in a context where the entire bitext has to be aligned and where alignment confidence measures have to be computed. Following much recent work, we study here a multi-pass approach: we first compute sure alignments that are used to train a discriminative model; then we use this model to fill in the gaps between sure links. Experimental results on several corpus show the effectiveness of this method as compared to alternative, state-of-the-art, proposals.
Fichier non déposé

Dates et versions

hal-01960678 , version 1 (19-12-2018)

Identifiants

  • HAL Id : hal-01960678 , version 1

Citer

Qian Yu, François Yvon, Aurã©lien Max. Revisiting sentence alignment algorithms for alignment visualization and evaluation. Workshop on Building and Using Comparable Corpora, ELRA, May 2012, Istanbul, Turkey. ⟨hal-01960678⟩
16 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More