What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages

Long Duong, Trevor Cohn, Karin Verspoor, Steven Bird, Paul Cook

Abstract

In this paper we address the problem of multilingual part-of-speech tagging for resource-poor languages. We use parallel data to transfer part-of-speech information from resource-rich to resourcepoor languages. Additionally, we use a small amount of annotated data to learn to “correct” errors from projected approach such as tagset mismatch between languages, achieving state-of-the-art performance (91.3%) across 8 languages. Our approach is based on modest data requirements, and uses minimum divergence classification. For situations where no universal tagset mapping is available, we propose an alternate method, resulting in state-of-the-art 85.6% accuracy on the resource-poor language Malagasy.
BibTeX
@inproceedings{duong2014what,
  author = {Long Duong and Trevor Cohn and Karin Verspoor and Steven Bird and Paul Cook},
  title = {{What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages}},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2014},
  doi = {10.3115/v1/d14-1096},
}
Figure