Can I read LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items on EtoBox?

LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items by Colla, Davide; Mensa, Enrico; Radicioni, Daniele P. is a Computer Science article available to read on EtoBox.

What is LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items about?

We present LESSLEX, a novel multilingual lexical resource. Different from the vast majority of existing approaches, we ground our embeddings on a sense inventory made available from the BabelNet semantic network. In this setting, multilingual access is governed by the mapping of terms onto their underlying sense descriptions, such that all vectors co-exist in the same semantic space. As a result, for each term we have thus the “blended” terminological vector along with those describing all senses associated to that term. LESSLEX has been tested on three tasks relevant to lexical semantics: conceptual similarity, contextual similarity, and semantic text similarity. We experimented over the principal data sets for such tasks in their multilingual and crosslingual variants, improving on or closely approaching state-of-the-art results. We conclude by arguing that LESSLEX vectors may be relevant for practical applications and for research on conceptual and lexical access and competence.

Who reads LessLex: Linking Multilingual Embeddings to SenSe Representations of LEXical Items?

Author

Colla, Davide; Mensa, Enrico; Radicioni, Daniele P.

Publisher

MIT Press; Cambridge MA: MIT Press Journals; MIT Press - Journals (ISSN 0891-2017)

Published

2020

Language

EN

Field

Computer Science (Physical Sciences)