How difficult is the adaptation of POS taggers?

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Domain adaptation is a difficult problem, but also a relevant one. Unsupervised domain adaptation focuses on adapting a model from a source domain, which includes plenty of labeled data, to a target domain that provides no labeled data. This is the most compelling setting of domain adaptation, but it is also the most difficult one. We perform an experimental analysis to highlight how difficult this problem is. We show that the best available unsupervised domain adaptation system for POS tagging can be outperformed by a simple POS tagger that has access to only 250 labeled sentences from the target domain. This is not a fair comparison between these two systems, of course; but it highlights that unsupervised domain adaptation is not well solved yet. Moreover, the best available systems are not yet practical, since they are complex, difficult to implement, and do not achieve significant improvements.

Original languageEnglish
Title of host publicationBRACIS 2017 : 2017 Brazilian Conference on Intelligent Systems : Uberlândia, MG, Brazil, 2-5 October 2017 : proceedings
Number of pages6
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date28.06.2017
Pages360-365
ISBN (print)978-1-5386-2408-1
ISBN (electronic)978-1-5386-2407-4
DOIs
Publication statusPublished - 28.06.2017
Externally publishedYes
EventBrazilian Conference on Intelligent Systems - BRACIS 2017 - Uberlandia, Brazil
Duration: 02.10.201705.10.2017
Conference number: 6

DOI