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

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

13 Sep 2022Findings (NAACL) 2022 7arXiv:2209.05869archive 2025-07-28

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang

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 making it impractical to be deployed to memory-limited devices. To address this issue, we delve into cross-lingual knowledge distillation and propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model. In our framework, contrastive learning, bottleneck, and parameter recurrent strategies are combined to prevent performance from being compromised during the compression process. The experimental results demonstrate that our method can compress the size of XLM-R and MiniLM by more than 50\%, while the performance is only reduced by about 1%.

PaperPDFConference PDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningKnowledge DistillationSemantic SimilaritySemantic Textual SimilarityXLM-R

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationXLM-R

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections