Pith. sign in

REVIEW 2 cited by

Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.01769 v2 pith:BUKWETKA submitted 2019-10-04 cs.CL cs.LGstat.ML

classification cs.CLcs.LGstat.ML
keywords modelsteacherdistillationhugestudentdatalargeperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use in practise for downstream tasks. Some recent efforts use knowledge distillation to compress these models. However, we see a gap between the performance of the smaller student models as compared to that of the large teacher. In this work, we leverage large amounts of in-domain unlabeled transfer data in addition to a limited amount of labeled training instances to bridge this gap for distilling BERT. We show that simple RNN based student models even with hard distillation can perform at par with the huge teachers given the transfer set. The student performance can be further improved with soft distillation and leveraging teacher intermediate representations. We show that our student models can compress the huge teacher by up to 26x while still matching or even marginally exceeding the teacher performance in low-resource settings with small amount of labeled data. Additionally, for the multilingual extension of this work with XtremeDistil (Mukherjee and Hassan Awadallah, 2020), we demonstrate massive distillation of multilingual BERT-like teacher models by upto 35x in terms of parameter compression and 51x in terms of latency speedup for batch inference while retaining 95% of its F1-score for NER over 41 languages.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 9 citations worldwide. Full citation record

  1. ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators

    cs.AR 2026-07 conditional novelty 6.0 of 10

    ADEPT selects CNN blocks for fine-tuning on PIM accelerators using a sensitivity-to-EDP ratio plus a selective channel-wise low-rank adapter, cutting training EDP by up to 8.1x with roughly unchanged accuracy.

  2. Differentiable Prompt Learning for Vision Language Models

    cs.LG 2024-12 conditional novelty 6.0 of 10

    DPL searches the per-layer prompt length for CLIP with differentiable architecture search, and reports higher few-shot accuracy than fixed-length prompt baselines.

Pith tools