RT Book,_Section
T1 Probing for idiomaticity in vector space models
A1 García González, Marcos
A1 Vieira, Tiago Kramer
A1 Scarton, Carolina
A1 Idiart, Marco
A1 Villavicencio, Aline
A2 Merlo, Paola
A2 Tiedemann, Jorg
A2 Tsarfaty, Reut
K1 Vector space models
K1 Word representation models
K1 Noun Compound Senses Dataset
K1 Word usages
AB Contextualised word representation models have been successfully used for capturing different word usages and they may be an attractive alternative for representing idiomaticity in language. In this paper, we propose probing measures to assess if some of the expected linguistic properties of noun compounds, especially those related to idiomatic meanings, and their dependence on context and sensitivity to lexical choice, are readily available in some standard and widely used representations. For that, we constructed the Noun Compound Senses Dataset, which contains noun compounds and their paraphrases, in context neutral and context informative naturalistic sentences, in two languages: English and Portuguese. Results obtained using four types of probing measures with models like ELMo, BERT and some of its variants, indicate that idiomaticity is not yet accurately represented by contextualised models
PB Association for Computational Linguistics
SN 978-1-954085-02-2
YR 2021
FD 2021-04
LK https://hdl.handle.net/10347/45969
UL https://hdl.handle.net/10347/45969
LA eng
NO Marcos Garcia, Tiago Kramer Vieira, Carolina Scarton, Marco Idiart, and Aline Villavicencio. 2021. Probing for idiomaticity in vector space models. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3551–3564, Online. Association for Computational Linguistics
NO Aline Villavicencio and Carolina Scarton are funded by the EPSRC project MIA: Modeling Idiomaticity in Human and Artificial Language Processing (EP/T02450X/1). Marcos García is funded by the Consellería de Cultura, Educación e Ordenación Universitaria  of the Galician Government (ERDF 2014-2020: Call ED431G 2019/04), and by a Ramón y Cajal grant (RYC2019-028473-I)
DS Minerva
RD 26 abr 2026