CoChat

Imitation Learning for Non-Autoregressive Neural Machine Translation

Open access
Wei, Bingzhen, Wang, Mingxuan, Zhou, Hao, Lin, Junyang, Sun, Xu · 2019 · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Cited by 65

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Abstract

Non-autoregressive translation models (NAT) have achieved impressive inference speedup.A potential issue of the existing NAT algorithms, however, is that the decoding is conducted in parallel, without directly considering previous context.In this paper, we propose an imitation learning framework for nonautoregressive machine translation, which still enjoys the fast translation speed but gives comparable translation performance compared to its auto-regressive counterpart.We conduct experiments on the IWSLT16, WMT14 and WMT16 datasets.Our proposed model achieves a significant speedup over the autoregressive models, while keeping the translation quality comparable to the autoregressive models.By sampling sentence length in parallel at inference time, we achieve the performance of 31.85BLEU on WMT16 Ro→En and 30.68 BLEU on IWSLT16 En→De.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/p19-1125

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Cited by

  • HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

    Wang, H., Wu, Z., Liu, Z., Cai, H., Zhu, L., Gan, C., & Han, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.686 · Cited by 227

    “Another trend is to apply non-or partially-autoregressive models to cut down the iteration number for decoding (Gu et al., 2019; Akoury et al., 2019; Wei et al., 2019; Gu et al., 2018).”
    Method
  • Glancing Transformer for Non-Autoregressive Neural Machine Translation

    Qian, L., Zhou, H., Bao, Y., Wang, M., Qiu, L., Zhang, W., Yu, Y., & Li, L. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.155 · Cited by 108

    “For GLAT, we first predict m target length candidates, then generate output sequences with argmax decoding for each target length candidate, which is also called length parallel decoding (LPD) (Wei et al., 2019).”
    BackgroundMethodInfluentialSelf-citation
  • Non-Autoregressive Line-Level Code Completion

    Liu, F., Fu, Z., Li, G., Jin, Z., Liu, H., Hao, Y., & Zhang, L. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3649594 · Cited by 22

    “…is performed in a fully-NAR way, where the input to the decoder H = { h 1 , h 2 , . . . , h n } are copied from the encoder output using soft-copy [52], which maps the encoder embeddings S = { s 1 , s 2 , . . . , s m } into target length H = { h 1 , h 2 , . . . , h n } depending on the distance…”
    Method

See all 65

Metadata

Authors
Wei, B., Wang, M., Zhou, H., Lin, J., & Sun, X.
Venue
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Published
2019
Pages
1304-1312
OpenAlex
W2962915948
Cited by
65
References
5
FWCI
4.01
Type
conference paper
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Imitation Learning for Non-Autoregressive Neural Machine Translation. https://app.cochat.ai/papers/10.18653/v1/p19-1125
The paper
Wei, B., Wang, M., Zhou, H., Lin, J., & Sun, X. (2019). Imitation Learning for Non-Autoregressive Neural Machine Translation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1125

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.