Finding next of kin: Cross-lingual embedding spaces for related languages. (4th March 2020)

• Record Type: Journal Article
• Authors: Sharoff, Serge
• Is Part Of: Natural language engineering. Volume 26:Part 2(2020)
• Page Start: 163
• Page End: 182
• Publication Date: 2020-03-04
• Subjects: Multilinguality, -- Text classification, -- Cross-lingual embeddings; Natural language processing (Computer science) -- Periodicals; Software engineering -- Periodicals; 006.35
• DOI: 10.1017/S1351324919000354
• Languages: English
• ISSNs: 1351-3249

Abstract

Abstract: Some languages have very few NLP resources, while many of them are closely related to better-resourced languages. This paper explores how the similarity between the languages can be utilised by porting resources from better- to lesser-resourced languages. The paper introduces a way of building a representation shared across related languages by combining cross-lingual embedding methods with a lexical similarity measure which is based on the weighted Levenshtein distance. One of the outcomes of the experiments is a Panslavonic embedding space for nine Balto-Slavonic languages. The paper demonstrates that the resulting embedding space helps in such applications as morphological prediction, named-entity recognition and genre classification.