Linguistic evaluation of translation errors in Chinese–English machine translations of patent titles
Published online: 4 September 2017
https://doi.org/10.1075/forum.15.1.08tsa
https://doi.org/10.1075/forum.15.1.08tsa
Abstract
The title of an invention allows the reader to understand the significance of a patent claim, and the wording of the title recurs throughout the subsequent patent documentation. If the translation of the title is erroneous, the quality of the translation in other parts of the patent documentation also suffers. This research involved using linguistic evaluation to identify common translation errors in Chinese–English machine translations of patent titles and examine the quality of machine-translated patent titles. Special focus was placed on orthographic, morphological, lexical, semantic, and syntactic errors found in patent titles. We sought to answer the following questions: (1) What are the trends in the application of machine translation in the Taiwan Intellectual Property Office (TIPO)? (2) How is the quality of machine translation controlled at TIPO? (3) What are common errors in machine-translated patent titles? Through analysis of our findings, it is possible to estimate the level of effort required from a posteditor following translation, and to suggest methods of improving machine translations of patent titles. This study also generates information applicable to the training of patent translators and posteditors.
Résumé
Le titre d'une invention permet au lecteur de comprendre l'importance d'une revendication de brevet et le libellé du titre revient dans la documentation de brevet subséquente. Si la traduction du titre est erronée, la qualité de la traduction dans d'autres parties de la documentation de brevet souffre également. Cette recherche a consisté à utiliser l'évaluation linguistique pour identifier les erreurs de traduction courantes dans les traductions automatiques en chinois et en anglais des titres de brevets et examiner la qualité des titres de brevet traduits par machine. Un accent particulier a été mis sur les erreurs orthographiques, morphologiques, lexicales, sémantiques et syntaxiques des titres de brevets. Nous avons cherché à répondre aux questions suivantes: (1) Quelles sont les tendances dans l'application de la traduction automatique à l'Office taiwanais de la propriété intellectuelle (TIPO)? (2) Comment la qualité de la traduction automatique est-elle contrôlée chez TIPO? (3) Quelles sont les erreurs courantes dans les brevets d'invention traduits par machine? Grâce à l'analyse de nos résultats, il est possible d'estimer le niveau d'effort requis d'un éditeur après la traduction et de proposer des méthodes d'amélioration de la traduction automatique de titres de brevets. Cette étude génère également des informations applicables à la formation des traducteurs et des expéditeurs de brevets.
Article outline
- 1.Introduction
- 2.Development of MT at TIPO
- 2.1Translation evaluation method at TIPO
- 2.2Using linguistic error classification to evaluate MT output
- 3.Research method and data collection
- 4.Analysing patent translation quality from patent title translation errors
- 4.1Orthographic errors
- 4.2Morphological errors
- 4.3Lexical errors
- 4.4Semantic errors
- 4.5Syntactic errors
- 5.Conclusion
- Acknowledgements
References
References (17)
Cross, Martin. 2007. “Literal Translation of Patents.” In The Patent Translator's Handbook, edited by Alison Carroll, 19–28. Virginia, USA: American Translators Association.
Dillinger, Mike, and Arle Lommel. 2004. LISA Best Practice Guide – Implementing Machine Translation. edited by Rebecca Ray. Switzerland.
Farrús, Mireia, Marta R. Costa-jussà, Jos´e B. Mariño, and Jos´e A. R. Fonollosa. 2010. “Linguistic-based evaluation criteria to identify statistical machine translation errors.” Proceedings of the 14th Annual Conference of the European Association for Machine Translation, Saint-Raphael, France, May, 2010.
Hsu, Jiuan-An. 2014. “Error Classification of Machine Translation A Corpus-based Study on Chinese-English Patent Translation.” Studies of Translation and Interpretation (18): 121–136.
Nelson, Kristopher A. 1998. “A Pretext for Writing: Prologues, Epilogues, and the Notion of Paratext.” SSRN eLibrary. .
O'Brien, Sharon. 2002. “Teaching Post-editing: A Proposal for Course Content.” Teaching Machine Translation – 6th International Workshop of the European Association for Machine Translation, Manchester, England, November 14–15.
Tager, Wolfgang. 2011. “The sentence-aligned European patent corpus.” 15th Conference of the European Association for Machine Translation, Leuven, Belgium.
Tinsley, John, Andy Way, and Paraic Sheridan. 2010. “PLuTO: MT for online patent translation.” AMTA 2010: the Ninth conference of the Association for Machine Translation in the Americas, Denver, Colorado, October 31–November 4, 2010.
. 2012. “Announcement.” TIPO. [URL].
Tsai, Yvonne. 2010. “Text Analysis of Patent Abstracts.” The Journal of Specialised Translation (13): 61–80.
Cited by (2)
Cited by two other publications
Gao, Yuan, Guangxian Xu & Qifa Lin
Lee, Jieun & Hyoeun Choi
2023. A quality assessment of Korean–English patent machine translation. FORUM. Revue internationale d’interprétation et de traduction / International Journal of Interpretation and Translation 21:2 ► pp. 236 ff.
This list is based on CrossRef data as of 8 november 2025. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.
