Pith. sign in

REVIEW 1 cited by

Partially Shuffling the Training Data to Improve Language 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 1903.04167 v2 pith:TJZESEOQ submitted 2019-03-11 cs.CL

classification cs.CL
keywords datatraininglanguageshufflingepochsmethodmodelingpartially
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Although SGD requires shuffling the training data between epochs, currently none of the word-level language modeling systems do this. Naively shuffling all sentences in the training data would not permit the model to learn inter-sentence dependencies. Here we present a method that partially shuffles the training data between epochs. This method makes each batch random, while keeping most sentence ordering intact. It achieves new state of the art results on word-level language modeling on both the Penn Treebank and WikiText-2 datasets.

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. Behavior Gated Language Models

    cs.CL 2019-08 conditional novelty 5.0 of 10

    Behavior-gated language models, which use a fixed behavior classifier's outputs to gate word predictions, achieve small perplexity reductions on therapy dialogues and Penn Treebank.

Pith tools