BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer

Tatiana Tsygankova, Stephen Mayhew, Dan Roth


Abstract
This paper describes the Cognitive Computation (CogComp) Group’s submissions to the multilingual named entity recognition shared task at the Balto-Slavic Natural Language Processing (BSNLP) Workshop. The final model submitted is a multi-source neural NER system with multilingual BERT embeddings, trained on the concatenation of training data in various Slavic languages (as well as English). The performance of our system on the official testing data suggests that multi-source approaches consistently outperform single-source approaches for this task, even with the noise of mismatching tagsets.
Anthology ID:
W19-3710
Volume:
Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tomaž Erjavec, Michał Marcińczuk, Preslav Nakov, Jakub Piskorski, Lidia Pivovarova, Jan Šnajder, Josef Steinberger, Roman Yangarber
Venue:
BSNLP
SIG:
SIGSLAV
Publisher:
Association for Computational Linguistics
Note:
Pages:
75–82
Language:
URL:
https://aclanthology.org/W19-3710
DOI:
10.18653/v1/W19-3710
Bibkey:
Cite (ACL):
Tatiana Tsygankova, Stephen Mayhew, and Dan Roth. 2019. BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer. In Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, pages 75–82, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
BSNLP2019 Shared Task Submission: Multisource Neural NER Transfer (Tsygankova et al., BSNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-3710.pdf