Automatic identification of multi-word expressions for Latvian and Lithuanian

ISSN: 2078-0958 (Print); ISSN: 2078-0966 (Online)We discuss an experiment on automatic identification of bi-gram multiword expressions for Latvian and Lithuanian. As these languages are considered to be underresourced in terms of lexical resources and availability or accuracy of special lexical tools (e.g. POS-tagger, parser), our approach uses raw corpora and combination of lexical association measures and supervised machine learning. We have achieved 92,4% precision and 52,2% recall for Latvian and 95,1% precision and 77,8% recall - for LithuanianBaltijos pažangių technologijų institutas, VilniusBaltijos pažangiųjų technologijų institutas, Vilnius. |liTaikomosios informatikos katedraVilniaus universitetas. |liVytauto Didžiojo universiteta