XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
TL
TL;DR
This paper introduces ELECTRA-style tasks to cross-lingual language model pre-training, and pretrain the model, named as XLM-E, on both multilingual and parallel corpora, which outperforms the baseline models on various cross-lingsual understanding tasks with much less computation cost.
Abstract
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability.
References55 items
1
Corrupted Image Modeling for Self-Supervised Visual Pre-Training
2
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training
3
DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders
4
Learning to Sample Replacements for ELECTRA Pre-Training
5