FLORS: Fast and Simple Domain Adaptation for Part-of-Speech Tagging

Tobias Schnabel, Hinrich Schütze


Abstract
We present FLORS, a new part-of-speech tagger for domain adaptation. FLORS uses robust representations that work especially well for unknown words and for known words with unseen tags. FLORS is simpler and faster than previous domain adaptation methods, yet it has significantly better accuracy than several baselines.
Anthology ID:
Q14-1002
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
15–26
Language:
URL:
https://aclanthology.org/Q14-1002
DOI:
10.1162/tacl_a_00162
Bibkey:
Cite (ACL):
Tobias Schnabel and Hinrich Schütze. 2014. FLORS: Fast and Simple Domain Adaptation for Part-of-Speech Tagging. Transactions of the Association for Computational Linguistics, 2:15–26.
Cite (Informal):
FLORS: Fast and Simple Domain Adaptation for Part-of-Speech Tagging (Schnabel & Schütze, TACL 2014)
Copy Citation:
PDF:
https://aclanthology.org/Q14-1002.pdf
Video:
 https://aclanthology.org/Q14-1002.mp4
Data
Penn Treebank