Pith. sign in

REVIEW 1 cited by

Optimal Completion Distillation for Sequence Learning

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 1810.01398 v2 pith:TNN7WQHV submitted 2018-10-02 cs.LG cs.AIcs.CLstat.ML

classification cs.LGcs.AIcs.CLstat.ML
keywords sequenceoptimalcompletiondistancedistillationeditefficientfirst
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by the model, we first identify the set of optimal suffixes that minimize the total edit distance, using an efficient dynamic programming algorithm. Then, for each position of the generated sequence, we use a target distribution that puts equal probability on the first token of all the optimal suffixes. OCD achieves the state-of-the-art performance on end-to-end speech recognition, on both Wall Street Journal and Librispeech datasets, achieving $9.3\%$ WER and $4.5\%$ WER respectively.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BEFL: Balancing Energy Consumption in Federated Learning for Mobile Edge IoT

    cs.LG 2024-12 conditional novelty 5.0 of 10

    BEFL is a client-selection framework for federated learning that jointly optimizes model accuracy, total device energy, and the variance of energy consumption across devices, evaluated on simulated CIFAR-10 and MNIST tasks.

Pith tools