Pregled bibliografske jedinice broj: 784064
Modeling Semantic Compositionality of Croatian Multiword Expressions
Modeling Semantic Compositionality of Croatian Multiword Expressions // Informatica (Ljubljana), 39 (2015), 3; 301-309 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 784064 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Modeling Semantic Compositionality of Croatian Multiword Expressions
Autori
Šnajder, Jan ; Almić, Petra
Izvornik
Informatica (Ljubljana) (0350-5596) 39
(2015), 3;
301-309
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
Multiword expressions; semantic composition; distributional semantics; Croatian language
Sažetak
A distinguishing feature of many multiword expressions (MWEs) is their semantic non-compositionality. Determining the semantic compositionality of MWEs is important for many natural language processing tasks. We address the task of modeling semantic compositionality of Croatian MWEs. We adopt a composition-based approach within the distributional semantics framework. We build and evaluate models based on Latent Semantic Analysis and the recently proposed neural network-based Skip-gram model, and experiment with different composition functions. We show that the compositionality scores predicted by the Skip-gram additive models correlate well with human judgments (=0.50). When framed as a classification task, the model achieves an accuracy of 0.64.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Profili:
Jan Šnajder
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Emerging Sources Citation Index (ESCI)
- Scopus