Multilingual Language Models for Named Entity Recognition in German and English

Antonia Baumann


Abstract
We assess the language specificity of recent language models by exploring the potential of a multilingual language model. In particular, we evaluate Google’s multilingual BERT (mBERT) model on Named Entity Recognition (NER) in German and English. We expand the work on language model fine-tuning by Howard and Ruder (2018), applying it to the BERT architecture. We successfully reproduce the NER results published by Devlin et al. (2019).Our results show that the multilingual language model generalises well for NER in the chosen languages, matching the native model in English and comparing well with recent approaches for German. However, it does not benefit from the added fine-tuning methods.
Anthology ID:
R19-2004
Volume:
Proceedings of the Student Research Workshop Associated with RANLP 2019
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
21–27
Language:
URL:
https://aclanthology.org/R19-2004
DOI:
10.26615/issn.2603-2821.2019_004
Bibkey:
Cite (ACL):
Antonia Baumann. 2019. Multilingual Language Models for Named Entity Recognition in German and English. In Proceedings of the Student Research Workshop Associated with RANLP 2019, pages 21–27, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Multilingual Language Models for Named Entity Recognition in German and English (Baumann, RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-2004.pdf