← Search

Rong Tian

2 accepted papers

2022

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

COLING 2022main

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferrin…

2022

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching

NAACL 2022findings

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this operation. Otherwise, its performance will drop sharply, thus makin…