Normal view MARC view ISBD view

Building and Evaluating a Distributional Memory for Croatian / Šnajder, Jan ; Padó, Sebastian ; Agić, Željko.

By: Šnajder, Jan.
Contributor(s): Padó, Sebastian [aut] | Agić, Željko [aut].
Material type: ArticleArticleDescription: in press str.Other title: Building and Evaluating a Distributional Memory for Croatian [Naslov na engleskom:].Subject(s): 2.09 | Distributional semantic model, distributional memory, dependency parsing, language resource, semantic similarity, Croatian language hrv | Distributional semantic model, distributional memory, dependency parsing, language resource, semantic similarity, Croatian language engOnline resources: Click here to access online In: 51st Annual Meeting of the Association for Computational Linguistics (4-9.08.2013. ; Sofia, Bugarska) Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) str. in pressSummary: 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.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

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.

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//