Kyoto-U: Syntactical EBMT System for NTCIR-7 Patent Translation Task
نویسندگان
چکیده
This paper describes “Kyoto-U” MT system that attended the patent translation task at NTCIR-7. Example-based machine translation is applied in this system to integrate our study on both structural NLP and machine translation. In the alignment step, consistency criteria are applied to solve the alignment ambiguities and to discard incorrect alignment candidates. In the translation step, translation examples are combined using “bond” information, which can handle the word ordering without any statistics.
منابع مشابه
EBMT System of KYOTO Team in PatentMT Task at NTCIR-9
This paper describes“KYOTO”EBMT system that attended PatentMT task at NTCIR-9. When translating very different language pairs such as Japanese-English and ChineseEnglish, it is very important to handle sentences in tree structures to overcome the difference. Some works incorporate tree structures in some parts of whole translation process, but not all the way from model training (parallel sente...
متن کاملFully Syntactic EBMT System of KYOTO Team in NTCIR-8
NTCIR-8 Patent Translation Task , Japan, Jun. 15-18, 2010 Intrinsic (BLEU) Extrinsic JE EJ BLEU MAP Recall@100 KYOTO 22.22 24.29 17.25 0.1909 0.5258 Moses 29.08 35.27 24.01 0.1943 0.5701 compoun s, espec a y tr met y a um num. Output:本発明は有機金属化合物特に トリメチルの浄化方法に関する 。 FIG. 4 is a plan view for illustrating the dimensional shape of waveguides used to simulate the stability of the optical intensity i...
متن کاملDescription of KYOTO EBMT System in PatentMT at NTCIR-10
This paper describes“KYOTO”EBMT system that attended PatentMT at NTCIR-10. When translating very different language pairs such as Japanese-English, it is very important to handle sentences in tree structures to overcome the difference. Many of recent studies incorporate tree structures in some parts of translation process, but not all the way from model training (parallel sentence alignment) to...
متن کاملNAIST-NTT System Description for Patent Translation Task at NTCIR-7
This paper proposes a semi-supervised approach to acquire domain specific translation knowledge from the collection of Wikipedia. The proposed method starts from a small number of seed translation pairs for each domain in a given corpus, and applies the regularized Laplacian to learn translation pairs relevant to the domain. This paper presents evaluation results using the NTCIR-7 Patent Transl...
متن کاملMachine Translation System for Patent Documents Combining Rule-based Translation and Statistical Postediting Applied to the NTCIR-10 PatentMT Task
In this article, we describe system architecture, preparation of training data and discussion on experimental results of the EIWA group in the NTCIR-10 Patent Translation Task. Our system is combining rule-based machine translation and statistical postediting. The thing about our new system compared with NTCIR-9 PatentMT task is to implement automatic selecting method from multiple translations...
متن کامل