CROSS-LINGUAL TRANSFER WITH CLASS-WEIGHTED LANGUAGE-INVARIANT REPRESENTATIONS

Ruicheng Xian, Heng Ji, Han Zhao

Research output: Contribution to conferencePaperpeer-review

Abstract

Recent advances in neural modeling have produced deep multilingual language models capable of extracting cross-lingual knowledge from non-parallel texts and enabling zero-shot downstream transfer. While their success is often attributed to shared representations, quantitative analyses are limited. Towards a better understanding, through empirical analyses, we show that the invariance of feature representations across languages-an effect of shared representations-strongly correlates with transfer performance. We also observe that distributional shifts in class priors between source and target language task data negatively affect performance, a largely overlooked issue that could cause negative transfer with existing unsupervised approaches. Based on these findings, we propose and evaluate a method for unsupervised transfer, called importance-weighted domain alignment (IWDA), that performs representation alignment with prior shift estimation and correction using unlabeled target language task data. Experiments demonstrate its superiority under large prior shifts, and show further performance gains when combined with existing semi-supervised learning techniques.

Original languageEnglish (US)
StatePublished - 2022
Event10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online
Duration: Apr 25 2022Apr 29 2022

Conference

Conference10th International Conference on Learning Representations, ICLR 2022
CityVirtual, Online
Period4/25/224/29/22

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Education
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'CROSS-LINGUAL TRANSFER WITH CLASS-WEIGHTED LANGUAGE-INVARIANT REPRESENTATIONS'. Together they form a unique fingerprint.

Cite this