Transfer Learning for Low-Resource Neural Machine Translation
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages.We present a transfer learning method that significantly improves BLEU scores across a range of low-resource languages.Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training.Using our transfer learning method we improve baseline NMT models by an average of 5.6 BLEU on four low-resource language pairs.Ensembling and unknown word replacement add another 2 BLEU which brings the NMT performance on low-resource machine translation close to a strong syntax based machine translation (SBMT) system, exceeding its performance on one language pair.Additionally, using the transfer learning model for re-scoring, we can improve the SBMT system by an average of 1.3 BLEU, improving the state-of-the-art on low-resource machine translation.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Backpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879 · cited 1×
“The models were trained to optimize maximum likelihood (via a softmax layer) with back-propagation through time (Werbos, 1990).”
MethodRecurrent Neural Network Regularization
Zaremba, W., Sutskever, I., & Vinyals, O. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.2329 · Cited by 2,123
Deep Learning of Representations for Unsupervised and Transfer Learning.
Bengio, Y. (2011) · Cited by 1,703
Addressing the Rare Word Problem in Neural Machine Translation
Luong, T., Sutskever, I., Le, Q., Vinyals, O., & Zaremba, W. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1002 · Cited by 619
Galley, M., Hopkins, M., Knight, K., & Marcu, D. (2004) · doi:10.21236/ada460212 · Cited by 460
Self-citationLiang, P., Taskar, B., & Klein, D. (2006) · Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics - · doi:10.3115/1220835.1220849 · Cited by 421
Cited by
A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Chen, X., & Wang, X. (2022) · ACM Computing Surveys · doi:10.1145/3447582 · Cited by 590
Transfer Learning in Natural Language Processing
Ruder, S., Peters, M. E., Swayamdipta, S., & Wolf, T. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-5004 · Cited by 587
Efficient Neural Architecture Search via Parameter Sharing
Pham, H., Guan, M. Y., Zoph, B., Le, Q. V., & Dean, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.03268 · Cited by 517
Self-citationA research agenda for augmented and virtual reality in architecture, engineering and construction
Davila Delgado, J. M., Oyedele, L., Demian, P., & Beach, T. (2020) · Advanced Engineering Informatics · doi:10.1016/j.aei.2020.101122 · Cited by 486
The Natural Language Decathlon: Multitask Learning as Question Answering
McCann, B., Keskar, N. S., Xiong, C., & Socher, R. (2018) · arXiv · doi:10.48550/arxiv.1806.08730 · Cited by 448
Massively Multilingual Neural Machine Translation
Aharoni, R., Johnson, M., & Firat, O. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1388 · Cited by 402
“The answer is not trivial: on the one hand, training multiple language pairs together may result in transfer learning (Zoph et al., 2016; Nguyen and Chiang, 2017).”
BackgroundNeural 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
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
Gong, X., Chang, S., Jiang, Y., & Wang, Z. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00332 · Cited by 305
Simple, Scalable Adaptation for Neural Machine Translation
Bapna, A., & Firat, O. (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/d19-1165 · Cited by 297
A Survey of Multilingual Neural Machine Translation
Dabre, R., Chu, C., & Kunchukuttan, A. (2021) · ACM Computing Surveys · doi:10.1145/3406095 · Cited by 294
An Analysis of Encoder Representations in Transformer-Based Machine Translation
Raganato, A., & Tiedemann, J. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5431 · Cited by 277
“Lastly, in order to check whether the learned information can be transferred across models, we use the encoder weights of a high-resource language pair to initialize a low-resource language pair, inspired by the work of Zoph et al. (2016).”
MethodResultInfluentialExploiting Source-side Monolingual Data in Neural Machine Translation
Zhang, J., & Zong, C. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1160 · Cited by 277
Unsupervised Pretraining for Sequence to Sequence Learning
Ramachandran, P., Liu, P., & Le, Q. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1039 · Cited by 251
“Various forms of transfer or multitask learning with seq2seq framework also have the flavors of our algorithm (Zoph et al., 2016; Luong et al., 2015; Firat et al., 2016).”
BackgroundAn Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
Chu, C., Dabre, R., & Kurohashi, S. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p17-2061 · Cited by 215
“However, it is reported that NMT works better than SMT only when there is an abundance of parallel corpora.”
BackgroundInfluentialAutomatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
Thompson, B., & Post, M. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.8 · Cited by 128
Pre-trained language model representations for language generation
Edunov, S., Baevski, A., & Auli, M. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1409 · Cited by 122
Multi-task Learning for Multilingual Neural Machine Translation
Wang, Y., Zhai, C., & Hassan, H. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.75 · Cited by 59
A pre-training and self-training approach for biomedical named entity recognition
Gao, S., Kotevska, O., Sorokine, A., & Christian, J. B. (2021) · PLOS ONE · doi:10.1371/journal.pone.0246310 · Cited by 46
Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank
Chau, E. C., Lin, L. H., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.118 · Cited by 44
“Lakew et al. (2018) and Zoph et al. (2016) perform additional training on parallel data to adapt bilingual translation models to unseen target languages, while Mueller et al. (2020) improve a polyglot task-specific model by finetuning on labeled monolingual data in the target variety.”
BackgroundCodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
Yan, W., Tian, Y., Li, Y., Chen, Q., & Wang, W. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.337 · Cited by 154
Question Generation With Doubly Adversarial Nets
Bao, J., Gong, Y., Duan, N., Zhou, M., & Zhao, T. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2859777 · Cited by 14
FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models
Dobler, K., & de Melo, G. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.829 · Cited by 8
“For vocabulary replacement with a language-specific tokenizer and random embedding initialization, we copy the original pretrained embeddings following Zoph et al. (2016).”
Method
Metadata
- Authors
- Zoph, B., Yuret, D., May, J., & Knight, K.
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Pages
- 1568-1575
- OpenAlex
- W2337363174
- Cited by
- 788
- References
- 19
- FWCI
- 41.93
- 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
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.