The efficacy of human post-editing for language translation
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Language translation is slow and expensive, so various forms of machine assistance have been devised. Automatic machine translation systems process text quickly and cheaply, but with quality far below that of skilled human translators. To bridge this quality gap, the translation industry has investigated post-editing, or the manual correction of machine output. We present the first rigorous, controlled analysis of post-editing and find that post-editing leads to reduced time and, surprisingly, improved quality for three diverse language pairs (English to Arabic, French, and German). Our statistical models and visualizations of experimental data indicate that some simple predictors (like source text part of speech counts) predict translation time, and that post-editing results in very different interaction patterns. From these results we distill implications for the design of new language translation interfaces.
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
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
Mixed-effects modeling with crossed random effects for subjects and items
Baayen, R. H., Davidson, D. J., & Bates, D. M. (2008) · Journal of Memory and Language · doi:10.1016/j.jml.2007.12.005 · Cited by 8,540
Regression Models for Ordinal Data
McCullagh, P. (1980) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1980.tb01109.x · Cited by 4,453
On the structural complexity of natural language sentences
Lin, D. (1996) · Proceedings of the 16th conference on Computational linguistics - · doi:10.3115/993268.993295 · Cited by 39 · cited 1×
“We annotated the source text with Stanford CoreNLP15 to obtain syntactic complexity [34], number of named entities, and part of speech tag counts.”
Method
Cited by
Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations
Wongsuphasawat, K., Moritz, D., Anand, A., Mackinlay, J., Howe, B., & Heer, J. (2016) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2467191 · Cited by 507
Self-citationThe Effects of Interactive Latency on Exploratory Visual Analysis
Liu, Z., & Heer, J. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2346452 · Cited by 326
Self-citationVoyager 2: Augmenting Visual Analysis with Partial View Specifications
Wongsuphasawat, K., Qu, Z., Moritz, D., Chang, R., Ouk, F., Anand, A., Mackinlay, J., Howe, B., & Heer, J. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025768 · Cited by 295
Self-citationAgency plus automation: Designing artificial intelligence into interactive systems
Heer, J. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1807184115 · Cited by 279
“As a baseline, we first compared purely manual translation with postediting (23), in which a human translator is given MT output and can revise (or delete) it as they see fit.”
Self-citationHuman Effort and Machine Learnability in Computer Aided Translation
Green, S., Wang, S. I., Chuang, J., Heer, J., Schuster, S., & Manning, C. D. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1130 · Cited by 68
“We previously proposed a fast, online tuning al-gorithm (Green et al., 2013b) based on AdaGrad (Duchi et al., 2011).”
BackgroundMethodSelf-citation
Metadata
- Authors
- Green, S., Heer, J., & Manning, C. D.
- Venue
- Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2013-04-27
- Pages
- 439-448
- OpenAlex
- W1986345088
- Cited by
- 186
- References
- 4
- FWCI
- 13.66
- Type
- conference paper
- Language
- en
- Open access
- closed
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.