Pith. sign in

REVIEW 2 cited by

XtremeDistil: Multi-stage Distillation for Massive Multilingual Models

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 2004.05686 v2 pith:BSJO5GDN submitted 2020-04-12 cs.CL cs.LG

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

Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use knowledge distillation to compress these huge models into shallow ones. In this work we study knowledge distillation with a focus on multi-lingual Named Entity Recognition (NER). In particular, we study several distillation strategies and propose a stage-wise optimization scheme leveraging teacher internal representations that is agnostic of teacher architecture and show that it outperforms strategies employed in prior works. Additionally, we investigate the role of several factors like the amount of unlabeled data, annotation resources, model architecture and inference latency to name a few. We show that our approach leads to massive compression of MBERT-like teacher models by upto 35x in terms of parameters and 51x in terms of latency 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. Full citation record

  1. Efficient Knowledge Injection in LLMs via Self-Distillation

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Self-distillation from a model's own in-context answers injects factual knowledge into LLM weights more efficiently than supervised fine-tuning and is competitive with RAG.

  2. AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer

    cs.CV 2025-05 conditional novelty 4.0 of 10

    A vision transformer reduces self-attention complexity from O(n^2) to O(mn) by using m learnable anchor tokens and a two-step Markov transition between anchors and tokens.

Pith tools