Human Associations Help to Detect Conventionalized Multiword Expressions

Abstract

In this paper we show that if we want to obtain human evidence about conventionalization of some phrases, we should ask native speakers about associations they have to a given phrase and its component words. We have shown that if component words of a phrase have each other as frequent associations, then this phrase can be considered as conventionalized. Another type of conventionalized phrases can be revealed using two factors: low entropy of phrase associations and low intersection of component word and phrase associations. The association experiments were performed for the Russian language.

Microsyntactic Unit Detection usingWord Embedding Models: Experiments on Slavic Languages

“…To predict the non-compositionality of an expression, we use cosine similarity between the expression vector representation v(w1w2) and the sum of the vector representations of the component words v(w1 + w2). This method has been extensively used in previous research on non-compositionality prediction (Mitchell and Lapata, 2010;Salehi et al, 2015;Cordeiro et al, 2016;Loukachevitch and Gerasimova, 2017;Nandakumar et al, 2018Nandakumar et al, , 2019, formally:…”