Naslov
Lexical Substitution for Evaluating Compositional Distributional Models

Autori
Buljan, Maja ; Pado, Sebastian ; Šnajder, Jan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) / - , 2018, 206-211

Skup
The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Mjesto i datum
New Orleans (LA), Sjedinjene Američke Države, 01.06.2018. - 06.06.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Compositional Distributional Semantic Models, lexical substitution

Sažetak
Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space. They have been predominantly evaluated on limited, artificial tasks such as semantic sentence similarity on hand-constructed datasets. This paper argues for lexical substitution (LexSub) as a means to evaluate CDSMs. LexSub is a more natural task, enables us to evaluate meaning composition at the level of individual words, and provides a common ground to compare CDSMs with dedicated LexSub models. We create a LexSub dataset for CDSM evaluation from a corpus with manual “all-words” LexSub annotation. Our experiments indicate that the Practical Lexical Function CDSM outperforms simple component-wise CDSMs and performs on par with the context2vec LexSub model using the same context.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA