Is Multilingual BERT Fluent in Language Generation?

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427144" target="_blank" >RIV/00216208:11320/19:10427144 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/W19-6204" target="_blank" >https://www.aclweb.org/anthology/W19-6204</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Is Multilingual BERT Fluent in Language Generation?

Original language description

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

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů