Is Multilingual BERT Fluent in Language Generation?

Samuel Rönnqvist, Jenna Kanerva, Tapio Salakoski, Filip Ginter


Abstract
The multilingual BERT model is trained on 104 languages and meant to serve as a universal language model and tool for encoding sentences. We explore how well the model performs on several languages across several tasks: a diagnostic classification probing the embeddings for a particular syntactic property, a cloze task testing the language modelling ability to fill in gaps in a sentence, and a natural language generation task testing for the ability to produce coherent text fitting a given context. We find that the currently available multilingual BERT model is clearly inferior to the monolingual counterparts, and cannot in many cases serve as a substitute for a well-trained monolingual model. We find that the English and German models perform well at generation, whereas the multilingual model is lacking, in particular, for Nordic languages. The code of the experiments in the paper is available at: https://github.com/TurkuNLP/bert-eval
Anthology ID:
W19-6204
Volume:
Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing
Month:
September
Year:
2019
Address:
Turku, Finland
Venues:
NoDaLiDa | WS
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
29–36
Language:
URL:
https://www.aclweb.org/anthology/W19-6204
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-6204.pdf