HICATS / JE : A Japanese - to - English Machine Translation System Based on Semantics
نویسنده
چکیده
We have been conducting a research and development aiming at practical machine translation systems. Our first product, HICATS/JE (Hitachi Computer Aided Translation System / Japanese to English), has been put on the market since May, 1986. The system can be used on HITAC M series computers / VOS3 operating system. It is intended to be utilized in translating documents primarily in scientific and technical field, e.g. manuals of products, research papers and patent abstracts.
منابع مشابه
Statistical Machine Translation with Rule based Machine Translation
We have evaluated the two-stage machine translation (MT) system. The first stage is a state-of-the-art trial rule-based machine translation system. The second stage is a normal statistical machine translation system. For Japanese-English machine translation, first, we used a Japanese-English rule-based MT, and we obtained "ENGLISH" sentences from Japanese sentences. Second, we used a standard s...
متن کاملLanguage Control for Effective Utilization of Hicats/je
The quality of machine translation results depends heavily on input texts. Language control will enable the maximum benefit to be drawn out from a machine translation system. Language control or pre-editing approaches are practicable in many circumstances a machine translation system is used to produce foreign language texts from native language texts, although cost-effectiveness should be of c...
متن کاملNICT at WAT 2015
Translation systems of our NICT team at the 2nd Workshop on Asian Translation (WAT 2015) are described in this paper. We participated in two translation tasks: Japanese-to-English (JE) and Korean-toJapanese (KJ). A baseline phrased-based (PB) statistical machine translation (SMT) system in Moses was used. On JE translation, two pre-reordering approaches were applied: a simple reverse preorderin...
متن کاملThe POSTECH Statistical Machine Translation Systems for NTCIR-7 Patent Translation Task
This paper describes the POSTECH statistical machine translation (SMT) systems for the NTCIR-7 patent translation task. We entered two patent translation subtasks: Japanese-to-English (KLE-je), and English-toJapanese translation (KLE-ej). The baseline systems are derived from a common phrase-based SMT framework. In addition, for Japanese-to-English translation, we adopted two kinds of methods. ...
متن کاملJapanese to English Machine Translation using Preordering and Compositional Distributed Semantics
The pipeline of modern statistical machine translation (SMT) systems consists of several stages, presenting interesting opportunities to tune it towards improved performance on distant language pairs like Japanese and English. We explore modifications to several parts of this pipeline. We include a preordering method in the preprocessing stage, a neural network based model in the tuning stage a...
متن کامل