Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources

Joo-Kyung Kim, Young-Bum Kim, Ruhi Sarikaya, Eric Fosler-Lussier


Abstract
Training a POS tagging model with crosslingual transfer learning usually requires linguistic knowledge and resources about the relation between the source language and the target language. In this paper, we introduce a cross-lingual transfer learning model for POS tagging without ancillary resources such as parallel corpora. The proposed cross-lingual model utilizes a common BLSTM that enables knowledge transfer from other languages, and private BLSTMs for language-specific representations. The cross-lingual model is trained with language-adversarial training and bidirectional language modeling as auxiliary objectives to better represent language-general information while not losing the information about a specific target language. Evaluating on POS datasets from 14 languages in the Universal Dependencies corpus, we show that the proposed transfer learning model improves the POS tagging performance of the target languages without exploiting any linguistic knowledge between the source language and the target language.
Anthology ID:
D17-1302
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2832–2838
URL:
https://www.aclweb.org/anthology/D17-1302
DOI:
10.18653/v1/D17-1302
Bib Export formats:
BibTeX MODS XML EndNote
Video:
 https://vimeo.com/238231953