Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?

12/21/2022
by   Ningyu Xu, et al.
0

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages. In this work, we investigate the distributions of grammatical relations induced from mBERT in the context of 24 typologically different languages. We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms. Such difference learnt via self-supervision plays a crucial role in the zero-shot transfer performance and can be predicted by variation in morphosyntactic properties between languages. These results suggest that mBERT properly encodes languages in a way consistent with linguistic diversity and provide insights into the mechanism of cross-lingual transfer.

READ FULL TEXT
research
04/17/2021

Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training

In recent years, pre-trained multilingual language models, such as multi...
research
05/09/2020

Finding Universal Grammatical Relations in Multilingual BERT

Recent work has found evidence that Multilingual BERT (mBERT), a transfo...
research
10/24/2022

Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models

Zero-shot cross-lingual transfer learning has been shown to be highly ch...
research
07/17/2020

Constructing a Family Tree of Ten Indo-European Languages with Delexicalized Cross-linguistic Transfer Patterns

It is reasonable to hypothesize that the divergence patterns formulated ...
research
09/27/2020

What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties

Multilingual sentence encoders have seen much success in cross-lingual m...
research
12/01/2021

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-Sentence Dependency Graph

We target the task of cross-lingual Machine Reading Comprehension (MRC) ...
research
10/16/2020

SIGTYP 2020 Shared Task: Prediction of Typological Features

Typological knowledge bases (KBs) such as WALS (Dryer and Haspelmath, 20...

Please sign up or login with your details

Forgot password? Click here to reset