Linguistic evaluation of translation errors in Chinese–English machine translations of patent titles

Abstract

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.