Pregled bibliografske jedinice broj: 633584
Building and Evaluating a Distributional Memory for Croatian
Building and Evaluating a Distributional Memory for Croatian // Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Sofija: Association for Computational Linguistics (ACL), 2013. str. 784-789 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 633584 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Building and Evaluating a Distributional Memory for Croatian
Autori
Šnajder, Jan ; Padó, Sebastian ; Agić, Željko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
/ - Sofija : Association for Computational Linguistics (ACL), 2013, 784-789
Skup
51st Annual Meeting of the Association for Computational Linguistics
Mjesto i datum
Sofija, Bugarska, 04.08.2013. - 09.08.2013
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Distributional semantic model; distributional memory; dependency parsing; language resource; semantic similarity; Croatian language
Sažetak
We report on the first structured distributional semantic model for Croatian, dm.hr. It is constructed after the model of the English Distributional Memory (Baroni and Lenci, 2010), from a dependency-parsed Croatian web corpus, and covers about 2M lemmas. We give details on the linguistic processing and the design principles. An evaluation shows state-of-the-art performance on a semantic similarity task with particularly good performance on nouns. The resource is freely available.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
