@inproceedings{marcosgarcia‚2021probing, title = {Probing for Idiomaticity in Vector Space Models}, booktitle = {16th Conference of the European Chapter of the Association for Computational Linguistics}, year = {2021}, abstract = {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.}, author = {Marcos Garcia‚ Tiago Kramer Vieira‚ Carolina Scarton‚ Marco Idiart‚ Aline Villavicencio} }