Domain adaptation of POS taggers without handcrafted features

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

Authors

Unsupervised domain adaptation is an attractive option when labeled data is lacking for some domain of interest but is available for other domain. Part-of-speech (POS) tagging is often considered a solved task when enough labeled data is available in the domain of interest. However, when considering a domain adaptation scenario, this is far from true. Several approaches have been proposed for domain adaptation of POS taggers, however as far as we know, all of them are based on handcrafted features. In this work, we employ a machine learning method whose input is exclusively composed of the raw text. This method learns word- and character-level representations (embeddings), and has been successfully applied to intra-domain tasks. We show that this method achieves strong performances on the domain adaptation of English and Portuguese POS taggers.

Original languageEnglish
Title of host publicationIJCNN 2017 : the International Joint Conference on Neural Networks
Number of pages8
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date30.06.2017
Pages3331-3338
Article number7966274
ISBN (print)978-1-5090-6183-9
ISBN (electronic)978-1-5090-6182-2
DOIs
Publication statusPublished - 30.06.2017
Externally publishedYes
EventInternational Joint Conference on Neural Networks - Anchorage, United States
Duration: 14.05.201719.05.2017
https://ieeexplore.ieee.org/xpl/conhome/7958416/proceeding