Pith. sign in

REVIEW 3 cited by

THUMT: An Open Source Toolkit for Neural Machine Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1706.06415 v1 pith:TOOCYZQT submitted 2017-06-20 cs.CL

Jiacheng Zhang , Yanzhuo Ding , Shiqi Shen , Yong Cheng , Maosong Sun , Huanbo Luan , Yang Liu This is my paper · ORCID
classification cs.CL
keywords thumttrainingneuraltoolkitmachineminimumrisktranslation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on top of Theano and supports three training criteria: maximum likelihood estimation, minimum risk training, and semi-supervised training. It features a visualization tool for displaying the relevance between hidden states in neural networks and contextual words, which helps to analyze the internal workings of NMT. Experiments on Chinese-English datasets show that THUMT using minimum risk training significantly outperforms GroundHog, a state-of-the-art toolkit for NMT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Improving Back-Translation with Uncertainty-based Confidence Estimation

    cs.CL 2019-08 accept novelty 6.0 of 10

    Uncertainty-based confidence estimation, computed with Monte Carlo Dropout, improves back-translation for NMT by weighting synthetic sentence pairs and reweighting attention, yielding consistent BLEU gains on Chinese-...

  2. Regularized Context Gates on Transformer for Machine Translation

    cs.CL 2019-08 conditional novelty 6.0 of 10

    Adding context gates with PMI-based regularization to Transformer decoder layers yields an average +1.0 BLEU across four translation tasks.

  3. Self-Attention with Structural Position Representations

    cs.CL 2019-09 conditional novelty 5.0 of 10

    Adding dependency-tree depth and distance as structural position encodings to Transformer attention improves BLEU by about 0.4 to 0.9 points on two translation tasks.

Pith tools