The DOI matches its Crossref record; 262 of the 262 references it cites were found in a registry or an index.
Neural Machine Translation: A Review
Open accessAbstract
The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Statistical MT, which mainly relies on various count-based models and which used to dominate MT research for decades, has largely been superseded by neural machine translation (NMT), which tackles translation with a single neural network. In this work we will trace back the origins of modern NMT architectures to word and sentence embeddings and earlier examples of the encoder-decoder network family. We will conclude with a short survey of more recent trends in the field.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Items 201–262 of 262
A Comparative Quality Evaluation of PBSMT and NMT using Professional Translators
Castilho, S., Moorkens, J., Gaspari, F., Sennrich, R., Sosoni, V., Georgakopoulou, Y., Lohar, P., Way, A., Barone, A. M., & Gialama, M. (2017) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 58
Sparse and Constrained Attention for Neural Machine Translation
Malaviya, C., Ferreira, P., & Martins, A. F. T. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2059 · Cited by 58
On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation
Alkhouli, T., Bretschner, G., & Ney, H. (2018) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w18-6318 · Cited by 58
Junczys-Dowmunt, M., Dwojak, T., & Sennrich, R. (2016) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w16-2316 · Cited by 55
Biasing Attention-Based Recurrent Neural Networks Using External Alignment Information
Alkhouli, T., & Ney, H. (2017) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w17-4711 · Cited by 55
Better Document-Level Machine Translation with Bayes’ Rule
Yu, L., Sartran, L., Stokowiec, W., Wang, L., Kong, L., Blunsom, P., & Dyer, C. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00319 · Cited by 54
Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015Preprint
Neubig, G., Morishita, M., & Nakamura, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.05203 · Cited by 51
Sequence to Sequence Mixture Model for Diverse Machine Translation
He, X., Haffari, G., & Norouzi, M. (2018) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k18-1056 · Cited by 50
An Operation Sequence Model for Explainable Neural Machine Translation
Stahlberg, F., Saunders, D., & Byrne, B. (2018) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/w18-5420 · Cited by 47
Self-citationPost-editing neural machine translation versus phrase-based machine translation for English–Chinese
Jia, Y., Carl, M., & Wang, X. (2019) · Machine Translation · doi:10.1007/s10590-019-09229-6 · Cited by 47
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search
Dahlmann, L., Matusov, E., Petrushkov, P., & Khadivi, S. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1148 · Cited by 46
Byte-based Neural Machine Translation
Costa‐jussà, M. R., Escolano, C., & Fonollosa, J. A. R. (2017) · Workshop on Subword and Character Level Models in NLP (SCLeM) · doi:10.18653/v1/w17-4123 · Cited by 41
Neishi, M., Sakuma, J., Tohda, S., Ishiwatari, S., Yoshinaga, N., & Toyoda, M. (2017) · Cited by 41
Pinnis, M., Krišlauks, R., Deksne, D., & Miks, T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-64206-2_27 · Cited by 39
Junczys-Dowmunt, M. (2018) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w18-6415 · Cited by 39
Bidirectional Generative Adversarial Networks for Neural Machine Translation
Zhang, Z., Liu, S., Li, M., Zhou, M. Q., & Chen, E. (2018) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k18-1019 · Cited by 39
Factored Neural Machine Translation Architectures
García-Martínez, M., Barrault, L., & Bougares, F. (2016) · HAL · Cited by 37
When and why are log-linear models self-normalizing?
Andreas, J., & Klein, D. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1027 · Cited by 34
What does Attention in Neural Machine Translation Pay Attention to?
Ghader, H., & Monz, C. (2017) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.1710.03348 · Cited by 34
Analyzing Neural MT Search and Model Performance
Niehues, J., Cho, E., Ha, T.-L., & Waibel, A. (2017) · doi:10.18653/v1/w17-3202 · Cited by 33
Kuchaiev, O., Ginsburg, B., Gitman, I., Lavrukhin, V., Case, C. T., & Micikevicius, P. (2018) · Workshop for NLP Open Source Software (NLP-OSS) · doi:10.18653/v1/w18-2507 · Cited by 33
Domain Adaptive Inference for Neural Machine Translation
Saunders, D., Stahlberg, F., de Gispert, A., & Byrne, B. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1022 · Cited by 33
Self-citation(2019) · doi:10.1609/aaai.v33i01.33016618 · Cited by 31
A Continuous Relaxation of Beam Search for End-to-End Training of Neural Sequence Models
Goyal, K., Neubig, G., Dyer, C., & Berg-Kirkpatrick, T. (2018) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v32i1.11806 · Cited by 31
Learning variable length units for SMT between related languages via Byte Pair Encoding
Kunchukuttan, A., & Bhattacharyya, P. (2017) · Workshop on Subword and Character Level Models in NLP (SCLeM) · doi:10.18653/v1/w17-4102 · Cited by 29
Schnober, C., Eger, S., Dinh, E.-L. D., & Gurevych, I. (2016) · TUbilio (Technical University of Darmstadt) · doi:10.48550/arxiv.1610.07796 · Cited by 29
Multi-Channel Encoder for Neural Machine Translation
Xiong, H., He, Z., Hu, X., & Wu, H. R. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11929 · Cited by 29
A Stable and Effective Learning Strategy for Trainable Greedy Decoding
Chen, Y., Li, V. O. K., Cho, K., & Bowman, S. R. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1035 · Cited by 29
Multi-representation ensembles and delayed SGD updates improve syntax-based NMT
Saunders, D., Stahlberg, F., de Gispert, A., & Byrne, B. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2051 · Cited by 27
Self-citationNMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning
Peris, Á., & Casacuberta, F. (2018) · The Prague Bulletin of Mathematical Linguistics · doi:10.2478/pralin-2018-0010 · Cited by 26
SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
Stahlberg, F., Hasler, E., Saunders, D., & Byrne, B. (2017) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/d17-2005 · Cited by 25
Self-citationMulti-Source Syntactic Neural Machine Translation
Currey, A., & Heafield, K. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1327 · Cited by 25
An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation
Morishita, M., Oda, Y., Neubig, G., Yoshino, K., Sudoh, K., & Nakamura, S. (2017) · doi:10.18653/v1/w17-3208 · Cited by 24
Neural Lattice Search for Domain Adaptation in Machine Translation
Khayrallah, H., Kumar, G., Duh, K., Post, M., & Koehn, P. (2017) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 24
Finding Better Subword Segmentation for Neural Machine Translation
Wu, Y., & Zhao, H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01716-3_5 · Cited by 23
Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors
Ruiz, N., Gangi, M. A. D., Bertoldi, N., & Federico, M. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1690 · Cited by 22
The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task
Rossenbach, N., Rosendahl, J., Kim, Y., Graça, M., Gokrani, A., & Ney, H. (2018) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w18-6487 · Cited by 20
Long, Z., Utsuro, T., Mitsuhashi, T., & Yamamoto, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.04521 · Cited by 19
Parallel Attention Mechanisms in Neural Machine Translation
Medina, J. R., & Kalita, J. K. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00088 · Cited by 18
Generalization and maximum likelihood from small data sets
Byrne, B. (2002) · Machine learning for signal processing ... · doi:10.1109/nnsp.1993.471869 · Cited by 17
Self-Attentive Residual Decoder for Neural Machine Translation
Werlen, L. M., Pappas, N., Ram, D., & Popescu-Belis, A. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-1124 · Cited by 17
A Smorgasbord of Features to Combine Phrase-Based and Neural Machine Translation
Marie, B., & Fujita, A. (2018) · Conference of the Association for Machine Translation in the Americas · Cited by 17
Deep Neural Machine Translation with Weakly-Recurrent UnitsPreprint
Gangi, M. A. D., & Federico, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.04185 · Cited by 16
Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016Preprint
Neubig, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.06542 · Cited by 16
Neural Machine Translation by Generating Multiple Linguistic Factors
García-Martínez, M., Barrault, L., & Bougares, F. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68456-7_2 · Cited by 15
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
Grundkiewicz, R., & Junczys-Dowmunt, M. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-2046 · Cited by 15
A Simple and Effective Approach to Coverage-Aware Neural Machine Translation
Li, Y., Xiao, T., Li, Y., Wang, Q., Xu, C., & Zhu, J. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2047 · Cited by 15
Improving Neural Machine Translation through Phrase-based Forced DecodingPreprint
Zhang, J., Utiyama, M., Sumita, E., Neubig, G., & Nakamura, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00309 · Cited by 14
A Comprehensive Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
Chu, C., Dabre, R., & Kurohashi, S. (2018) · Journal of Information Processing · doi:10.2197/ipsjjip.26.529 · Cited by 14
Speed or accuracy? a study in evaluation of simultaneous speech translation
Mieno, T., Neubig, G., Sakti, S., Toda, T., & Nakamura, S. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-498 · Cited by 13
Variable-Length Word Encodings for Neural Translation Models
Chitnis, R., & DeNero, J. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1249 · Cited by 12
Deconvolution-Based Global Decoding for Neural Machine TranslationPreprint
Lin, J., Sun, X., Ren, X., Ma, S., Su, J., & Su, Q. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03692 · Cited by 11
Faster decoding for subword level Phrase-based SMT between related languagesPreprint
Kunchukuttan, A., & Bhattacharyya, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.00354 · Cited by 9
An error analysis for image-based multi-modal neural machine translation
Calixto, I., & Liu, Q. (2019) · Machine Translation · doi:10.1007/s10590-019-09226-9 · Cited by 9
Why not be Versatile? Applications of the SGNMT Decoder for Machine TranslationPreprint
Stahlberg, F., Saunders, D., Iglesias, G., & Byrne, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.07204 · Cited by 8
Self-citationKey-value Attention Mechanism for Neural Machine Translation
Mino, H., Utiyama, M., Sumita, E., & Tokunaga, T. (2017) · International Joint Conference on Natural Language Processing · Cited by 7
Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning
Gülçehre, Ç., Dutil, F., Trischler, A., & Bengio, Y. (2017) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w17-2627 · Cited by 6
CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
Wang, X., Utiyama, M., & Sumita, E. (2018) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/d18-2023 · Cited by 6
Deeper Machine Translation and Evaluation for German
Avramidis, E., Macketanz, V., Burchardt, A., Helcl, J., & Uszkoreit, H. (2016) · Cited by 5
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Iglesias, G., Tambellini, W., de Gispert, A., Hasler, E., & Byrne, B. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-3013 · Cited by 3
Regularizing Forward and Backward Decoding to Improve Neural Machine Translation
Yang, Z. C., Chen, L., & Nguyen, L.-M. (2018) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse.2018.8573433 · Cited by 3
Handling Many-To-One UNK Translation for Neural Machine Translation
Li, F., Du, Q., Wang, Q., Xiao, T., & Zhu, J. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7134-8_10 · Cited by 1
Cited by
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Kalyan, K. S. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100048 · Cited by 335
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
CURE: Code-Aware Neural Machine Translation for Automatic Program Repair
Jiang, N., Lutellier, T., & Tan, L. (2021) · 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) · doi:10.1109/icse43902.2021.00107 · Cited by 290
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
Knowledge Editing for Large Language Models: A Survey
Wang, S., Zhu, Y., Liu, H., Zheng, Z., Chen, C., & Li, J. (2025) · ACM Computing Surveys · doi:10.1145/3698590 · Cited by 79
Metadata
- Authors
- Stahlberg, F.
- Venue
- Journal of Artificial Intelligence Research
- Publisher
- AI Access Foundation
- Published
- 2020-10-02
- Volume
- 69
- Pages
- 343-418
- ISSN
- 1076-9757 (ISSN-L)
- OpenAlex
- W2992693294
- Cited by
- 397
- References
- 262
- FWCI
- 13.83
- Type
- journal article
- Language
- en
- Open access
- diamond
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
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.