A Study of Reinforcement Learning for Neural Machine Translation
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system.However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged.In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning.We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL training.Furthermore, to fill in the gap that it remains unclear whether RL is still beneficial when monolingual data is used, we propose a new method to leverage RL to further boost the performance of NMT systems trained with source/target monolingual data.By integrating all our findings, we obtain competitive results on WMT14 English-German, WMT17 English-Chinese, and WMT17 Chinese-English translation tasks, especially setting a state-of-the-art performance on WMT17 Chinese-English translation task.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 3×
“However, to obtain state-of-the-art (SOTA) performance, it is essential to leverage recently derived deep models (Gehring et al., 2017; Vaswani et al., 2017), which are much more powerful.”
BackgroundA Structured Self-attentive Sentence Embedding
Lin, Z., Feng, M., Santos, C. N. D., Yu, M., Xiang, B., Zhou, B., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.03130 · Cited by 1,743 · cited 1×
“…between Transformer and previous RNNSearch (Bahdanau et al., 2015) or ConvS2S (Gehring et al., 2017) is that Transformer relies entirely on self-attention (Lin et al., 2017) to compute representations of source and target side sentences, without using recurrent or convolutional operations.”
BackgroundDeep Reinforcement Learning That Matters
Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., & Meger, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11694 · Cited by 1,685
Sequence Level Training with Recurrent Neural Networks
Ranzato, M., Chopra, S., Auli, M., & Zaremba, W. (2015) · arXiv · doi:10.48550/arxiv.1511.06732 · Cited by 1,426 · cited 11×
“In practice, REIN-FORCE (Williams, 1992) is usually leveraged to approximate the above expectation via sampling ˆ y from the policy p ( y | x ) , leading to the objective as maximizing: Throughout the paper we will use REINFORCE as our policy optimization method for RL training.”
BackgroundMethodResultInfluentialNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1162 · Cited by 974 · cited 2×
“We use byte pair encoding (BPE) (Sennrich et al., 2015b) to pre-process the source and target sentences, forming source-side and target-side dictionary with 40 , 000 and 37 , 000 types, respectively.”
MethodNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Findings of the 2016 Conference on Machine Translation
Bojar, O., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huck, M., Jimeno Yepes, A., Koehn, P., Logacheva, V., Monz, C., et al. (2016) · Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers · doi:10.18653/v1/w16-2301 · Cited by 539 · cited 6×
“For the bilingual datasets, WMT17 (Bojar et al., 2017) En-Zh 1 and WMT17 Zh-En use the same dataset, which contains about 24 M sentences pairs, including CWMT Corpus 2017 and UN Parallel Corpus V1.”
MethodInfluential
Cited by
Deep Reinforcement Learning: A Survey
Wang, X., Wang, S., Liang, X., Zhao, D., Huang, J., Xu, X., Dai, B., & Miao, Q. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3207346 · Cited by 972
Neural Machine Translation: A Review
Stahlberg, F. (2020) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12007 · Cited by 397
Neural Machine Translation for Low-resource Languages: A Survey
Ranathunga, S., Lee, E.-S. A., Prifti Skenduli, M., Shekhar, R., Alam, M., & Kaur, R. (2023) · ACM Computing Surveys · doi:10.1145/3567592 · Cited by 313
Survey on reinforcement learning for language processing
Uc-Cetina, V., Navarro-Guerrero, N., Martin-Gonzalez, A., Weber, C., & Wermter, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10205-5 · Cited by 177
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
Choshen, L., Fox, L., Aizenbud, Z., & Abend, O. (2019) · arXiv · doi:10.48550/arxiv.1907.01752 · Cited by 28
“The per-token sampling as done in our experiments is more exploratory than beam search (Wu et al., 2018), reducing P K E.”
Method
Metadata
- Authors
- Wu, L., Tian, F., Qin, T., Lai, J., & Liu, T.-Y.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 3612-3621
- OpenAlex
- W2888442053
- Cited by
- 157
- References
- 12
- FWCI
- 10.30
- 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: A Study of Reinforcement Learning for Neural Machine Translation. https://app.cochat.ai/papers/10.18653/v1/d18-1397
- The paper
- Wu, L., Tian, F., Qin, T., Lai, J., & Liu, T.-Y. (2018). A Study of Reinforcement Learning for Neural Machine Translation. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/d18-1397
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.