TY - GEN
T1 - Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging
AU - Plank, Barbara
AU - Agic, Zeljko
PY - 2018
Y1 - 2018
N2 - We introduce DSDS: a cross-lingual neural part-of-speech tagger that learns from dis- parate 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.
AB - We introduce DSDS: a cross-lingual neural part-of-speech tagger that learns from dis- parate 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.
KW - Cross-lingual part-of-speech tagging
KW - Distant supervision
KW - Low-resource languages
KW - Morphological lexicons
KW - Annotation projection
UR - https://aclanthology.coli.uni-saarland.de/papers/D18-1061/d18-1061
M3 - Article in proceedings
BT - Proceedings of the Conference on Empirical Methods in Natural Language Processing
PB - Association for Computational Linguistics
ER -