Papers › Natural Language Generation for Effective Knowledge Distillation

Natural Language Generation for Effective Knowledge Distillation

1 Nov 2019WS 2019 11archive 2025-07-28

Raphael Tang, Yao Lu, Jimmy Lin

Knowledge distillation can effectively transfer knowledge from BERT, a deep language representation model, to traditional, shallow word embedding-based neural networks, helping them approach or exceed the quality of other heavyweight language representation models. As shown in previous work, critical to this distillation procedure is the construction of an unlabeled transfer dataset, which enables effective knowledge transfer. To create transfer set examples, we propose to sample from pretrained language models fine-tuned on task-specific text. Unlike previous techniques, this directly captures the purpose of the transfer set. We hypothesize that this principled, general approach outperforms rule-based techniques. On four datasets in sentiment classification, sentence similarity, and linguistic acceptability, we show that our approach improves upon previous methods. We outperform OpenAI GPT, a deep pretrained transformer, on three of the datasets, while using a single-layer bidirectional LSTM that runs at least ten times faster.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

castorini/d-bert officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Distilling Task-Specific Knowledge from BERT into Simple Neural Networks (arXiv:1903.12136; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Knowledge DistillationLinguistic AcceptabilitySentenceSentence SimilaritySentiment AnalysisSentiment ClassificationText GenerationTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLSTMLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiece

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