| Type of publication: | Article in the peer-reviewed foreign international conference proceedings (P1d);Straipsnis recenzuojamoje užsienio tarptautinės konferencijos medžiagoje (P1d) |
| Field of Science: | Computer science (N009);Informatika (N009) |
| Author(s): | Krilavičius, Tomas;Mandravickaitė, Justina |
| Title: | Identification of multiword expressions for Latvian and Lithuanian: hybrid approach |
| Is part of: | EACL 2017: 13th workshop on multiword expressions, April 4, 2017 Valencia, Spain: proceedings of the workshop. Stroudsburg : Association for Computational Linguistics, 2017 |
| Extent: | p. 97-101 |
| Date: | 2017 |
| Note: | This research was funded by a grant (No. LIP- 027/2016) from the Research Council of Lithuania |
| Keywords: | Hybrid methods;Lexical association measures;Machines learning |
| ISBN: | 9781945626487 |
| Abstract: | We discuss an experiment on automatic identification of bi-gram multiword expressions in parallel Latvian and Lithuanian corpora. Raw corpora, lexical association measures (LAMs) and supervised machine learning (ML) are used due to deficit and quality of lexical resources (e.g., POS-tagger, parser) and tools. While combining LAMs with ML is rather effective for other languages, it has shown some nice results for Lithuanian and Latvian as well. Combining LAMs with ML we have achieved 92,4% precision and 52,2% recall for Latvian and 95,1% precision and 77,8% recall for Lithuanian |
| Internet: | https://hdl.handle.net/20.500.12259/36623
https://hdl.handle.net/20.500.12259/36623 |
| Affiliation(s): | Informatikos fakultetas
Vytauto Didžiojo universitetas
Baltijos pažangiųjų technologijų institutas
Taikomosios informatikos katedra |
| Appears in Collections: | 3. Konferencijų medžiaga / Conference materials
Universiteto mokslo publikacijos / University Research Publications
|
