Simple task-specific bilingual word embeddings

TY - GEN

T1 - Simple task-specific bilingual word embeddings

AU - Gouws, Stephan

AU - Søgaard, Anders

PY - 2015

Y1 - 2015

N2 - We introduce a simple wrapper method that uses off-the-shelf word embedding algorithms to learn task-specific bilingual word embeddings. We use a small dictionary of easily-obtainable task-specific word equivalence classes to produce mixed context-target pairs that we use to train off-the-shelf embedding models. Our model has the advantage that it (a) is independent of the choice of embedding algorithm, (b) does not require parallel data, and (c) can be adapted to specific tasks by re-defining the equivalence classes. We show how our method outperforms off-the-shelf bilingual embeddings on the task of unsupervised cross-language part-of-speech (POS) tagging, as well as on the task of semi-supervised cross-language super sense (SuS) tagging.

AB - We introduce a simple wrapper method that uses off-the-shelf word embedding algorithms to learn task-specific bilingual word embeddings. We use a small dictionary of easily-obtainable task-specific word equivalence classes to produce mixed context-target pairs that we use to train off-the-shelf embedding models. Our model has the advantage that it (a) is independent of the choice of embedding algorithm, (b) does not require parallel data, and (c) can be adapted to specific tasks by re-defining the equivalence classes. We show how our method outperforms off-the-shelf bilingual embeddings on the task of unsupervised cross-language part-of-speech (POS) tagging, as well as on the task of semi-supervised cross-language super sense (SuS) tagging.

M3 - Article in proceedings

SN - 978-1-941643-49-5

SP - 1386

EP - 1390

BT - Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics

ER -