Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT).We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences similar in some aspect and (2) gradual inclusion of some sentence types as the training progresses (so called "curriculum learning").In our English-to-Czech experiments, the internal homogeneity of minibatches has no effect on the training but some of our "curricula" achieve a small improvement over the baseline.
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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 7×
“very quick overfitting as we discuss in Section 4.5. If the network was presented only with the more difficult examples, its performance on theeasy ones would drop. Some mixing strategy is thus needed. Bengio et al. (2009) propose a relatively simple strategy. They organize all training data into bins ofsimilarcomplexit…”
BackgroundInfluential
Cited by
A Survey on Curriculum Learning
Wang, X., Chen, Y., & Zhu, W. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3069908 · Cited by 692
“…include the number of objects in images in the task of semantic segmentation [122]; the number of coordinating conjunctions (e.g., “and”, “or”) [50] or phrases (e.g., prepositional phrases) [113]; the parse tree depth [113] that measures the sentence complexity in the view of grammar; and the…”
BackgroundInfluentialSoviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01611-x · Cited by 431
Competence-based Curriculum Learning for Neural Machine Translation
Platanios, E. A., Stretcu, O., Neubig, G., Poczos, B., & Mitchell, T. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-1119 · Cited by 304
Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems
Xu, Q., Ali, S., & Yue, T. (2023) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3582571 · Cited by 49
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
Abbe, E., Bengio, S., Lotfi, A., & Rizk, K. (2023) · arXiv · doi:10.48550/arxiv.2301.13105 · Cited by 4
“Interestingly, some works in the natural processing domain have used the length of the sentences (possibly along with other properties) to design their curriculum strategy (Spitkovsky et al., 2010; Zaremba & Sutskever, 2014; Kocmi & Bojar, 2017; Platanios et al., 2019).”
Background
Metadata
- Authors
- Charles University, F. O. M. A. P., Kocmi, T., & Bojar, O.
- Venue
- RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning
- Publisher
- Incoma Ltd. Shoumen, Bulgaria
- Published
- 2017-11-10
- Pages
- 379-386
- OpenAlex
- W2741838462
- Cited by
- 110
- References
- 3
- FWCI
- 4.57
- 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: Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. https://app.cochat.ai/papers/10.26615/978-954-452-049-6_050
- The paper
- Charles University, F. O. M. A. P., Kocmi, T., & Bojar, O. (2017). Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning. https://doi.org/10.26615/978-954-452-049-6_050
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.