UNAL-NLP: Cross-Lingual Phrase Sense Disambiguation with Syntactic Dependency Trees
Emilio Silva-Schlenker, Sergio Jiménez, Julia Baquero · 2014
In this paper we describe our participation in the SemEval 2014, Task 5, consisting of the construction of a translation assistance system that translates L1 fragments, written in L2 context, to their correct L2 translation.Our approach consists of a bilingual parallel corpus, a system of syntactic features extraction and a statistical memory-based classification algorithm.Our system ranked 4th and 6th among the 10 participating systems that used the English-Spanish data set.