In order to automatically identify noun synonyms, we propose a new idea which opposes classical polysemous representations of words to monosemous representations based on the “one sense per discourse” hypothesis. For that purpose, we apply the attributional similarity paradigm on two levels: corpus and document. We evaluate our methodology on well-known standard multiple choice synonymy questio...

The present paper notes that the lexical item PO, literally meaning ‘to break’, bears multiple semantic imports in Mandarin Chinese. Given the lack of well-documented research on the semantics of the lexical item, this paper aims to explore the various meanings of PO. By examining the collocations of PO, thirteen meanings are identified, with predicative and attributive senses. It is proposed t...

Abstract Individual differences and polysemy have rich literatures in cognitive linguistics, but little is said about the prospect of individual polysemy. This article reports an investigation that sought to establish whether people vary senses a polysemous word they find meaningful, develop novel methodology study The combined established tools: sentence-sorting tasks, rarely used statistical ...

Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge lexical polysemy remains unclear. We propose a novel experimental setup for analyzing this in LMs specifically trained different languages (English, French, Spanish, and Greek) multilingual BERT. perform our analysis on datasets carefully designed to reflect sense distributions, control para...

this paper examines the semantic contribution of -?r and -andeh suffixes in persian based on lieber’s (2004) lexical semantic representation. this framework using six semantic features ([material], [dynamic], [location], [ieps] , [b] and [ci] and a principle called coordination principle studies the semantic contribution of lexical items including affixes and their functions in compounding, der...