Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Fully non-autoregressive neural machine translation (NAT) simultaneously predicts tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline.In this work, we target on closing the performance gap while maintaining the latency advantage.We first inspect the fundamental issues of fully NAT models, and adopt dependency reduction in the learning space of output tokens as the primary guidance.Then, we revisit methods in four different aspects that have been proven effective for improving NAT models, and carefully combine these techniques with necessary modifications.Our extensive experiments on three translation benchmarks show that the proposed system achieves the state-of-the-art results for fully NAT models, and obtains comparable performance with the autoregressive and iterative NAT systems.For instance, one of the proposed models achieves 27.49BLEU points on WMT14 En-De with 16.5× speed-up compared to similar sized autoregressive baseline under the same inference condition.The implementation of our model is available here 1 .
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.
Integrity signals
Registry
Cites
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.
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
Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · Proceedings of the Third Conference on Machine Translation: Research Papers · doi:10.18653/v1/w18-6319 · Cited by 2,112
A Call for Clarity in Reporting BLEU Scores
Post, M. (2018) · arXiv · doi:10.48550/arxiv.1804.08771 · Cited by 2,111
Sequence-Level Knowledge Distillation
Kim, Y., & Rush, A. M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1139 · Cited by 836
Mask-Predict: Parallel Decoding of Conditional Masked Language Models
Ghazvininejad, M., Levy, O., Liu, Y., & Zettlemoyer, L. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1633 · Cited by 464
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
Lee, J., Mansimov, E., & Cho, K. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1149 · Cited by 386
Analyzing Uncertainty in Neural Machine Translation
Ott, M., Auli, M., Grangier, D., & Ranzato, M. (2018) · arXiv · doi:10.48550/arxiv.1803.00047 · Cited by 140
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
Cited by
MaskGIT: Masked Generative Image Transformer
Chang, H., Zhang, H., Jiang, L., Liu, C., & Freeman, W. T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01103 · Cited by 446
Erdem, E., Kuyu, M., Yagcioglu, S., Frank, A., Parcalabescu, L., Plank, B., Babii, A., Turuta, O., Erdem, A., Calixto, I., et al. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12918 · Cited by 54
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
Xia, H., Ge, T., Wang, P., Chen, S.-Q., Wei, F., & Sui, Z. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.257 · Cited by 40
“…NAR models, including training with alignment-based objectives (Libovický and Helcl, 2018; Ghazvininejad et al., 2020; Saharia et al., 2020; Gu and Kong, 2021; Shao and Feng, 2022), modeling dependencies between target to-kens (Ghazvininejad et al., 2019; Shu et al., 2020; Qian et al., 2021; Bao…”
BackgroundAccelerating Transformer Inference for Translation via Parallel Decoding
Santilli, A., Severino, S., Postolache, E., Maiorca, V., Mancusi, M., Marin, R., & Rodola, E. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.689 · Cited by 29
Lossless Acceleration for Seq2seq Generation with Aggressive Decoding
Ge, T., Xia, H., Sun, X., Chen, S.-Q., & Wei, F. (2022) · arXiv · doi:10.48550/arxiv.2205.10350 · Cited by 6
Metadata
- Authors
- Gu, J., & Kong, X.
- Venue
- Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
- Published
- 2021
- Pages
- 120-133
- OpenAlex
- W3177172118
- Cited by
- 80
- References
- 8
- FWCI
- 8.64
- Type
- conference paper
- Language
- en
- Open access
- gold
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: Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade. https://app.cochat.ai/papers/10.18653/v1/2021.findings-acl.11
- The paper
- Gu, J., & Kong, X. (2021). Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. https://doi.org/10.18653/v1/2021.findings-acl.11
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.