Skip to main navigation Skip to search Skip to main content

Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer

  • Ziqing Yang
  • , Wentao Ma
  • , Yiming Cui
  • , Jiani Ye
  • , Wanxiang Che
  • , Shijin Wang
  • IFLYTEK Co., Ltd.
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine reading comprehension task MLQA and natural language interface task XNLI. The results show that WEAM can significantly improve the zero-shot performance.

Original languageEnglish
Title of host publicationProceedings of the 3rd Workshop on Machine Reading for Question Answering, MRQA 2021
EditorsAdam Fisch, Alon Talmor, Danqi Chen, Eunsol Choi, Minjoon Seo, Patrick Lewis, Robin Jia, Sewon Min
PublisherAssociation for Computational Linguistics (ACL)
Pages100-105
Number of pages6
ISBN (Electronic)9781954085954
StatePublished - 2021
Event3rd Workshop on Machine Reading for Question Answering, MRQA 2021 - Punta Cana, Dominican Republic
Duration: 10 Nov 2021 → …

Publication series

NameProceedings of the 3rd Workshop on Machine Reading for Question Answering, MRQA 2021

Conference

Conference3rd Workshop on Machine Reading for Question Answering, MRQA 2021
Country/TerritoryDominican Republic
CityPunta Cana
Period10/11/21 → …

Fingerprint

Dive into the research topics of 'Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer'. Together they form a unique fingerprint.

Cite this