Effective Compositional Model for Lexical Alignment

Béatrice Daille (1) , Emmanuel Morin (1)

1 LS2N - équipe TALN - Traitement Automatique du Langage Naturel

The automatic compilation of bilingual dictionaries from comparable corpora has been successful for single-word terms (SWTs), but remains disappointed for multi-word terms (MWTs). The increase of coverage of bilingual dictionary thanks to compositional translation improved the results, but still shows some limits for MWTs of different syntactic structures. In this paper, we propose to bridge the gap between syntactic structures through morphological links. The results show a significant improvement in the compositional translation of MWTs that demonstrate the efficiency of the morphologically based-method for lexical alignment.

Keywords: lexical alignment; comparable corpora; terminology

Domains: Computation and Language [cs.CL]

Béatrice Daille, Emmanuel Morin. Effective Compositional Model for Lexical Alignment. IJCNLP 2008: Third International Joint Conference on Natural Language Processing, Jan 2008, Hyderabad, India. pp.95-102. ⟨hal-00403643⟩