Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging

Barbara Plank, Željko Agić


Abstract
a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance selection, tag dictionaries, morphological lexicons, and distributed representations, all in a uniform framework. The approach is simple, yet surprisingly effective, resulting in a new state of the art without access to any gold annotated data.
Anthology ID:
D18-1061
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
614–620
Language:
URL:
https://aclanthology.org/D18-1061
DOI:
10.18653/v1/D18-1061
Bibkey:
Cite (ACL):
Barbara Plank and Željko Agić. 2018. Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 614–620, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging (Plank & Agić, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1061.pdf
Video:
 https://aclanthology.org/D18-1061.mp4
Code
 bplank/bilstm-aux