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

Barbara Plank, Zeljko Agic

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

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.
OriginalsprogEngelsk
TitelProceedings of the Conference on Empirical Methods in Natural Language Processing
ForlagAssociation for Computational Linguistics
Publikationsdato2018
StatusUdgivet - 2018

Fingeraftryk

Dyk ned i forskningsemnerne om 'Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging'. Sammen danner de et unikt fingeraftryk.

Citationsformater