Pith. sign in

REVIEW 4 cited by

Bridging the Gap between Training and Inference 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 1906.02448 v2 pith:Y4ORQVW7 submitted 2019-06-06 cs.CL cs.LGstat.ML

Wen Zhang , Yang Feng , Fandong Meng , Di You , Qun Liu This is my paper · ORCID
classification cs.CLcs.LGstat.ML
keywords sequencecontexttrainingwordsgroundtranslationtruthinference
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese->English and WMT'14 English->German translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Stable On-Policy Distillation through Adaptive Target Reformulation

    cs.LG 2026-01 unverdicted novelty 7.0 of 10

    Veto replaces the teacher's target distribution with a product of teacher and student probabilities, stabilizing on-policy knowledge distillation and improving small-model benchmarks.

  2. Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

    cs.CV 2026-02 unverdicted novelty 6.0 of 10

    Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.

  3. VideoMAR: Autoregressive Video Generatio with Continuous Tokens

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A decoder-only autoregressive video model with continuous tokens, frame-wise causal attention, and a next-frame diffusion loss reports a higher VBench-I2V score than Cosmos I2V with a much smaller model and dataset.

  4. Taming Teacher Forcing for Masked Autoregressive Video Generation

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Complete Teacher Forcing, conditioning masked frames on complete previous frames instead of masked ones, substantially improves frame-level autoregressive video generation quality and temporal coherence.

Pith tools