Lexical Resources for Low-Resource PoS Tagging in Neural Times

Barbara Plank, Sigrid Klerke

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer 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.
OriginalsprogEngelsk
TitelProceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19)
ForlagAssociation for Computational Linguistics
Publikationsdato2019
Sider25–34
ISBN (Elektronisk)978-91-7929-995-8
StatusUdgivet - 2019
NavnNEALT (Northern European Association of Language Technology) Proceedings Series
ISSN1736-6305

Emneord

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

Fingeraftryk

Dyk ned i forskningsemnerne om 'Lexical Resources for Low-Resource PoS Tagging in Neural Times'. Sammen danner de et unikt fingeraftryk.

Citationsformater