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.
|Titel||Proceedings of the Conference on Empirical Methods in Natural Language Processing|
|Forlag||Association for Computational Linguistics|
|Status||Udgivet - 2018|