Taking on new challenges in multi-word unit processing for machine translation
Johanna Monti, Anabela Marques Barreiro, Annibale Elia, Federica Marano, Antonella Napoli · RECERCAT (Consorci de Serveis Universitaris de Catalunya) · 2011
This paper discusses the qualitative comparative evaluation performed on the results of two machine translation systems with different approaches to the processing of multi-word units. It proposes a solution for overcoming the difficulties multi-word units present to machine translation by adopting a methodology that combines the lexicon grammar approach with OpenLogos ontology and semantico-syntactic rules. The paper also discusses the importance of a qualitative evaluation metrics to correctly evaluate the performance of machine translation engines with regards to multi-word units.