Colex2Lang: Language Embeddings from Semantic Typology

Yiyi Chen*, Russa Biswas, Johannes Bjerva

*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

21 Downloads (Pure)

Abstract

In semantic typology, colexification refers to words with multiple meanings, either related (polysemy) or unrelated (homophony). Studies of cross-linguistic colexification have yielded insights into, e.g., psychology, historical linguistics and cognitive science (Xu et al., 2020; Brochhagen and Boleda, 2022; Schapper and Koptjevskaja-Tamm, 2022). While NLP research up until now has mainly focused on integrating syntactic typology (Naseem et al., 2012; Ponti et al., 2019; Chaudhary et al., 2019; Üstün et al., 2020; Ansell et al., 2021; Oncevay et al., 2022), we here investigate the potential of incorporating semantic typology, of which colexification is an example. We propose a framework for constructing a large-scale synset graph and learning language representations with node embedding algorithms. We demonstrate that cross-lingual colexification patterns provide a distinct signal for modelling language similarity and predicting typological features. Our representations achieve a 9.97% performance gain in predicting lexico-semantic typological features and expectantly contain a weaker syntactic signal. This study is the first attempt to learn language representations and model language similarities using semantic typology at a large scale, setting a new direction for multilingual NLP, especially for low-resource languages.
Original languageEnglish
Title of host publicationProceedings of the 24rd Nordic Conference on Computational Linguistics (NoDaLiDa)
PublisherAssociation for Computational Linguistics
Publication date22 May 2023
Pages673-684
Publication statusPublished - 22 May 2023
EventThe 24th Nordic Conference on Computational Linguistics - Tórshavn, Faroe Islands
Duration: 22 May 202324 May 2023
https://www.nodalida2023.fo/

Conference

ConferenceThe 24th Nordic Conference on Computational Linguistics
Country/TerritoryFaroe Islands
CityTórshavn
Period22/05/202324/05/2023
Internet address

Keywords

  • Natural Language Processing
  • Semantic Typology

Fingerprint

Dive into the research topics of 'Colex2Lang: Language Embeddings from Semantic Typology'. Together they form a unique fingerprint.

Cite this