Learning a POS tagger for AAVE-like language
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
POS taggers trained on newswire perform much worse on domains such as subtitles, lyrics, and tweets. In addition, these domains are very heterogeneous, and it is not clear what data to annotate to learn a POS tagger for subtitles, for example. In this paper we consider the problem of learning a POS tagger for subtitles, lyrics, and tweets associated with African-American Vernacular English from a previously released and manually annotated Twitter corpus. Our approach is to learn from a mixture of this data and unlabeled data, which was automatically and partially labeled using mined tag dictionaries. Our POS tagger obtains a tagging accuracy of 89% on subtitles, 85% on lyrics, and 83% on tweets, with up to 55% error reductions over a state-of-the-art newswire POS tagger, and 15-25% error reductions over a state-of-the-art Twitter POS tagger.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of NAACL-HLT 2016 |
Antal sider | 6 |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2016 |
Sider | 1115-1120 |
ISBN (Elektronisk) | ISBN 978-1-941643-91-4 |
Status | Udgivet - 2016 |
Begivenhed | NAACL - San Diego, San Diego, USA Varighed: 12 jun. 2016 → 17 jun. 2016 |
Konference
Konference | NAACL |
---|---|
Lokation | San Diego |
Land | USA |
By | San Diego |
Periode | 12/06/2016 → 17/06/2016 |
Links
- http://www.aclweb.org/anthology/N16-1130
Forlagets udgivne version
ID: 167551969