In this article the operational principles of MT in business English translation is briefly introduced with an aim to point out that to improve the MT quality machine study is a key factor to work on.
Scientific literature often contains abbreviated terms in English for brief.Machine translation(MT)systems can help to share knowledge in different languages among researchers.Current MT systems may translate the same...Scientific literature often contains abbreviated terms in English for brief.Machine translation(MT)systems can help to share knowledge in different languages among researchers.Current MT systems may translate the same abbreviated term in different sentences into different target terms.MT systems translate the abbreviated term in two ways:one is to use translation of the full name,the other is to use the abbreviated term directly.Abbreviated terms may be ambiguous and polysemous,and MT systems do not have an explicit strategy to decide which way to use without context information.To get the consistent translation for abbreviated terms in scientific literature,this paper proposes a translation model for abbreviated terms that integrates context information to get consistent translation of abbreviated terms.The context information includes the positions of abbreviated term and domain attributes of scientific literature.The first abbreviated term is translated in full name while the latter ones of the same abbreviated term will show the abbreviated form in the translation text.Experiments of translation from Chinese to English show the effectiveness of the proposed translation model.展开更多
A representation schema called translation corresponding tree （TCT） has been applied to a Portuguese to Chinese example-based machine translation system, The translation examples are annotated by the representation ...A representation schema called translation corresponding tree （TCT） has been applied to a Portuguese to Chinese example-based machine translation system, The translation examples are annotated by the representation of the TCT structure. Each TCT describes not only the syntactic structure of the source sentence （i.e., Portuguese in our system） but also the translation correspondences （i.e., Chinese translation）, In addition, the TCT nodes describe the corresponding linguistic relationships between the source and target languages. The translation examples can be effectively represented with this annotation schema and organized in the bilingual knowledge database or example base. In the real machine translation process, the target language is synthesized with higher quality by referring to the TCT translation information.展开更多
文摘In this article the operational principles of MT in business English translation is briefly introduced with an aim to point out that to improve the MT quality machine study is a key factor to work on.
基金the National Key Research and Development Program of China(No.2019YFA0707201)ISTIC Research Foundation Project(No.ZD2020-10)。
文摘Scientific literature often contains abbreviated terms in English for brief.Machine translation(MT)systems can help to share knowledge in different languages among researchers.Current MT systems may translate the same abbreviated term in different sentences into different target terms.MT systems translate the abbreviated term in two ways:one is to use translation of the full name,the other is to use the abbreviated term directly.Abbreviated terms may be ambiguous and polysemous,and MT systems do not have an explicit strategy to decide which way to use without context information.To get the consistent translation for abbreviated terms in scientific literature,this paper proposes a translation model for abbreviated terms that integrates context information to get consistent translation of abbreviated terms.The context information includes the positions of abbreviated term and domain attributes of scientific literature.The first abbreviated term is translated in full name while the latter ones of the same abbreviated term will show the abbreviated form in the translation text.Experiments of translation from Chinese to English show the effectiveness of the proposed translation model.
基金Supported by the Center of Scientific and Technological Research of University of Macao Under Grant CATIVO: 3678
文摘A representation schema called translation corresponding tree （TCT） has been applied to a Portuguese to Chinese example-based machine translation system, The translation examples are annotated by the representation of the TCT structure. Each TCT describes not only the syntactic structure of the source sentence （i.e., Portuguese in our system） but also the translation correspondences （i.e., Chinese translation）, In addition, the TCT nodes describe the corresponding linguistic relationships between the source and target languages. The translation examples can be effectively represented with this annotation schema and organized in the bilingual knowledge database or example base. In the real machine translation process, the target language is synthesized with higher quality by referring to the TCT translation information.
