Lexical Resources for Low-Resource PoS Tagging in Neural Times

Barbara Plank, Sigrid Klerke

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

More and more evidence is appearing that integrating symbolic lexical knowledge into neural models aids learning. This contrasts the widely-held belief that neural networks largely learn their own feature representations. For example, recent work has shown benefits of integrating lexicons to aid cross-lingual part-of-speech (PoS). However, little is known on how complementary such additional information is, and to what extent improvements depend on the coverage and quality of these external resources. This paper seeks to fill this gap by providing a thorough analysis on the contributions of lexical resources for cross-lingual PoS tagging in neural times.
Original languageEnglish
Title of host publicationProceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19)
PublisherAssociation for Computational Linguistics
Publication date2019
Pages25–34
ISBN (Electronic)978-91-7929-995-8
Publication statusPublished - 2019
SeriesNEALT (Northern European Association of Language Technology) Proceedings Series
ISSN1736-6305

Keywords

  • Symbolic lexical knowledge
  • Neural models
  • Cross-lingual part-of-speech tagging
  • Lexical resources
  • Neural feature representations

Fingerprint

Dive into the research topics of 'Lexical Resources for Low-Resource PoS Tagging in Neural Times'. Together they form a unique fingerprint.

Cite this