Papers › The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding...

The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning

31 May 2019arXiv:1906.00095archive 2025-07-28

Bonggun Shin, Hao Yang, Jinho D. Choi

Recent advances in deep learning have facilitated the demand of neural models for real applications. In practice, these applications often need to be deployed with limited resources while keeping high accuracy. This paper touches the core of neural models in NLP, word embeddings, and presents a new embedding distillation framework that remarkably reduces the dimension of word embeddings without compromising accuracy. A novel distillation ensemble approach is also proposed that trains a high-efficient student model using multiple teacher models. In our approach, the teacher models play roles only during training such that the student model operates on its own without getting supports from the teacher models during decoding, which makes it eighty times faster and lighter than other typical ensemble methods. All models are evaluated on seven document classification datasets and show a significant advantage over the teacher models for most cases. Our analysis depicts insightful transformation of word embeddings from distillation and suggests a future direction to ensemble approaches using neural models.

PaperPDFCode

Code

bgshin/distill_demo officialmentioned in papertf report

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

Document ClassificationEnsemble LearningSentiment AnalysisWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis CR STM+TSED+PT+2L Accuracy 82.73 #9 of 9 Archive leaderboard report
Sentiment Analysis MPQA STM+TSED+PT+2L Accuracy 89.83 #2 of 4 Archive leaderboard report
Sentiment Analysis MR STM+TSED+PT+2L Accuracy 80.09 #10 of 19 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification STM+TSED+PT+2L Accuracy 86.95 #75 of 87 Archive leaderboard report
Sentiment Analysis SST-5 Fine-grained classification STM+TSED+PT+2L Accuracy 49.14 #23 of 31 Archive leaderboard report
Subjectivity Analysis SUBJ STM+TSED+PT+2L Accuracy 92.34 #14 of 19 Archive leaderboard report
Text Classification TREC-6 STM+TSED+PT+2L Error 7.04 #14 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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