Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Correcting Length Bias in Neural Machine Translation

Open access
Murray, Kenton, Chiang, David · 2018 · Proceedings of the Third Conference on Machine Translation: Research Papers

Abstract

We study two problems in neural machine translation (NMT).First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT.Second, NMT has a tendency to produce translations that are too short.Here, we argue that these problems are closely related and both rooted in label bias.We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/w18-6322

Cites

0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

The publisher hasn’t deposited this paper’s reference list.

Research works printed but not linked: 23

  1. [1]1. Daniel Andor, Chris Alberti, David Weiss, Aliaksei Severyn, Alessandro Presta, Kuzman Ganchev, Slav Petrov, and Michael Collins. 2016. Globally nor- malized transition-based neural networks. In Proc. ACL, pages 2442-2452.
  2. [2]2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In Proc. ICLR.
  3. [3]3. Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Shujian Huang, Matthias Huck, Philipp Koehn, Qun Liu, Varvara Logacheva, et al. 2017. Findings of the 2017 Con- ference on Machine Translation (WMT17). In Proc. Conference on Machine Translation, pages 169- 214.
  4. [5]5. Léon Bottou. 1991. Une Approche théorique de l'Apprentissage Connexioniste; Applications à la re- connaissance de la Parole. Ph.D. thesis, Université de Paris Sud.
  5. [6]6. Nicolas Boulanger-Lewandowski, Yoshua Bengio, and Pascal Vincent. 2013. Audio chord recognition with recurrent neural networks. In ISMIR, pages 335- 340.
  6. [7]7. Michael Denkowski and Alon Lavie. 2014. Meteor universal: Language specific translation evaluation for any target language. In Proc. Workshop on Sta- tistical Machine Translation.
  7. [8]8. Michael Denkowski and Graham Neubig. 2017. Stronger baselines for trustable results in neural ma- chine translation. In Proceedings of the First Work- shop on Neural Machine Translation, pages 18-27.
  8. [9]9. Wei He, Zhongjun He, Hua Wu, and Haifeng Wang. 2016. Improved neural machine translation with SMT features. In Proc. AAAI.
  9. [10]10. Liang Huang, Kai Zhao, and Mingbo Ma. 2017. When to finish? optimal beam search for neural text gen- eration (modulo beam size). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2134-2139.
  10. [11]11. Sébastien Jean, Orhan Firat, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2015. Montreal neural machine translation systems for wmt'15. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 134-140.
  11. [12]12. Philipp Koehn and Rebecca Knowles. 2017. Six chal- lenges for neural machine translation. In Pro- ceedings of the First Workshop on Neural Machine Translation, pages 28-39.
  12. [13]13. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling se- quence data. In Proc. ICML, pages 282-289.
  13. [15]15. Graham Neubig. 2016. Lexicons and minimum risk training for neural machine translation: NAIST- CMU at WAT2016. In Proceedings of the 3rd Work- shop on Asian Translation, pages 119-125.
  14. [16]16. Franz Josef Och. 2003. Minimum error rate training in statistical machine translation. In Proc. ACL, pages 160-167.
  15. [17]17. Franz Josef Och and Hermann Ney. 2002. Discrim- inative training and maximum entropy models for statistical machine translation. In Proc. ACL, pages 295-302. Association for Computational Linguis- tics.
  16. [18]18. Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proc. ACL, pages 311-318.
  17. [19]19. Michael Paul, Marcello Federico, and Sebastian Stüker. 2010. Overview of the IWSLT 2010 evaluation cam- paign. In International Workshop on Spoken Lan- guage Translation (IWSLT) 2010.
  18. [21]21. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proc. ACL, pages 1715-1725.
  19. [22]22. Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2016. Minimum risk training for neural machine translation. In Proc. of ACL.
  20. [23]23. Arun Venkatraman, Martial Hebert, and J Andrew Bagnell. 2015. Improving multi-step prediction of learned time series models. In AAAI, pages 3024- 3030.
  21. [24]24. Sam Wiseman and Alexander M Rush. 2016. Sequence-to-sequence learning as beam-search op- timization. In Proceedings of EMNLP.
  22. [26]26. Yilin Yang, Liang Huang, and Mingbo Ma. 2018. Breaking the beam search curse: A study of (re- )scoring methods and stopping criteria for neural machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing.
  23. [27]27. Yue Zhang and Joakim Nivre. 2012. Analyzing the effect of global learning and beam-search on transition-based dependency parsing. In Proceed- ings of COLING 2012: Posters, pages 1391-1400.

Cited by

See all 138

Metadata

Authors
Murray, K., & Chiang, D.
Affiliations
University of Notre Dame (US)
Venue
Proceedings of the Third Conference on Machine Translation: Research Papers
Published
2018
Pages
212-223
OpenAlex
W2889317799
Cited by
133
References
0
Citations by year
2026: 1 · 2025: 8 · 2024: 8 · 2023: 15 · 2022: 17 · 2021: 25 · 2020: 45 · 2019: 12 · 2018: 2
FWCI
8.57
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Conference on Machine Translation (WMT) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • University of Southern California
  • Defense Advanced Research Projects Agency (HR0011, HR0011-15-C-0115)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
Keywords
neural machine translation, length bias, beam search, label bias, perceptron algorithm, translation length

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: Correcting Length Bias in Neural Machine Translation. https://app.cochat.ai/papers/10.18653/v1/w18-6322
The paper
Murray, K., & Chiang, D. (2018). Correcting Length Bias in Neural Machine Translation. Proceedings of the Third Conference on Machine Translation: Research Papers. https://doi.org/10.18653/v1/w18-6322

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.