Syntax-augmented Multilingual BERT for Cross-lingual Transfer

06/03/2021
by   Wasi Uddin Ahmad, et al.
0

In recent years, we have seen a colossal effort in pre-training multilingual text encoders using large-scale corpora in many languages to facilitate cross-lingual transfer learning. However, due to typological differences across languages, the cross-lingual transfer is challenging. Nevertheless, language syntax, e.g., syntactic dependencies, can bridge the typological gap. Previous works have shown that pre-trained multilingual encoders, such as mBERT <cit.>, capture language syntax, helping cross-lingual transfer. This work shows that explicitly providing language syntax and training mBERT using an auxiliary objective to encode the universal dependency tree structure helps cross-lingual transfer. We perform rigorous experiments on four NLP tasks, including text classification, question answering, named entity recognition, and task-oriented semantic parsing. The experiment results show that syntax-augmented mBERT improves cross-lingual transfer on popular benchmarks, such as PAWS-X and MLQA, by 1.4 and 1.6 points on average across all languages. In the generalized transfer setting, the performance boosted significantly, with 3.9 and 3.1 points on average in PAWS-X and MLQA.

READ FULL TEXT
09/03/2019

Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks

We present Unicoder, a universal language encoder that is insensitive to...
05/12/2022

Lifting the Curse of Multilinguality by Pre-training Modular Transformers

Multilingual pre-trained models are known to suffer from the curse of mu...
02/24/2022

Oolong: Investigating What Makes Crosslingual Transfer Hard with Controlled Studies

Little is known about what makes cross-lingual transfer hard, since fact...
08/24/2020

Cross-lingual Semantic Role Labeling with Model Transfer

Prior studies show that cross-lingual semantic role labeling (SRL) can b...
04/18/2021

mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs

Multilingual T5 (mT5) pretrains a sequence-to-sequence model on massive ...
08/31/2021

Cross-Lingual Text Classification of Transliterated Hindi and Malayalam

Transliteration is very common on social media, but transliterated text ...
03/24/2020

Cross-Lingual Adaptation Using Universal Dependencies

We describe a cross-lingual adaptation method based on syntactic parse t...