SZTAKI HLT | efnilex-vect


2014 - 2015

efnilex-vect: word embeddings in European translation

The EFNILEX project has explored the use of machine translation tools for lexicon generation in "medium" European languages (less-resourced official languages of th EU). In 2012, dictionaries have been generated from parallel corpora. Since 2014, we have followed the method of Mikolov et al (2013): dictionaries are generated from monolingual corpora plus a seed dictionary. In 2015, we targeted disambiguation in two ways: scoring translations inferred in pivot-based fashion from Wiktionary with wikt2dict, and translating from multi-prototype embeddings.

Learn more


Project leader