Naslov
Random Indexing Distributional Semantic Models for Croatian Language

Autori
Janković, Vedrana ; Šnajder, Jan ; Dalbelo Bašić, Bojana

Izvornik
Lecture notes in Artificial Intelligence (Text, Speech and Dialogue, 14th International Conference, TSD 2011, Pilsen, Czech Republic, September 2011) (0302-9743) 6836 (2011); 411-418

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Janković; Vedrana; Šnajder; Jan; Dalbelo Bašić; Bojana
(Distributional semantic model; computational semantics; random indexing; Croatian language)

Sažetak
Distributional semantic models (DSMs) model semantic relations between expressions by comparing the contexts in which these expressions occur. This paper presents an extensive evaluation of distributional semantic models for Croatian language. We focus on random indexing models, an efficient and scalable approach to building DSMs. We build a number of models with different parameters (dimension, context type, and similarity measure) and compare them against human semantic similarity judgments. Our results indicate that even low-dimensional random indexing models may outperform the raw frequency models, and that the choice of the similarity measure is most important.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA