English-Japanese machine translation
نویسندگان
چکیده
A fully transistorized computer for the purpose of experimental machine translation from English to Japanese was recently completed, and a program test is now being conducted. This paper describes the organization of this special purpose computer named Yamato as well as the translation principles and the program flow diagrams. Yamato, whose switching elements use 600 transistors and 7,000 germanium diodes, can work with both variable and fixed word length, executes 46 different instructions of a one-plus-one address code and stores data on a magnetic drum holding 820,000 bits. This drum holds four dictionaries: word, idiom, syntax, and Japanese word, as well as a translation program of about 4,000 words of 32 bits. Upon consulting the word dictionary , each word of a given sentence is transformed into an eight character item of information which includes its grammatical features and the location of the corresponding Japanese word. Since the grammatical structures of the two languages are quite different, word for word translation, such as might be possible between European languages, is generally unsuccessful. The program described is designed to find the grammatical structure of the given English sentence and to transpose the words in it so as to meet the corresponding Japanese grammar. After the transposition is made, each eight character word is translated into Japanese with the use of the fourth dictionary, and then typed out. It takes about ten seconds to translate a simple sentence such as "I have some eggs in my hand", including the time required for input and output.
منابع مشابه
A Prototype English-Japanese Machine Translation System for Translating IBM Computer Manuals
This paper describes a prototype English-Japanese machine translation (MT) system developed at the Science Institute of IBM Japan, Ltd. This MT system currently aims at the translation of IBM computer manuals. It is based on a transfer approach in which the transfer phase is divided into two sub-phases: English transformation and Engllsh-Japanese conversion. An outline of the system and a detai...
متن کاملUtilizing Semantic Equivalence Classes of Japanese Functional Expressions in Translation Rule Acquisition from Parallel Patent Sentences
In the “Sandglass” MT architecture, we identify the class of monosemous Japanese functional expressions and utilize it in the task of translating Japanese functional expressions into English. We employ the semantic equivalence classes of a recently compiled large scale hierarchical lexicon of Japanese functional expressions. We then study whether functional expressions within a class can be tra...
متن کاملUQAM's System Description for the NTCIR-10 Japanese and English PatentMT Evaluation Tasks
This paper describes the development of a Japanese-English and English-Japanese translation system for the NTCIR-10 Patent MT tasks. The MT system is based on the provided training data and Moses decoder. We report our first attempt on statistical machine translation for these pairs of languages and the Patent domain.
متن کاملAutomatic Integrated Dictionary Systems
0. Introduction 1. AidTrans Project 2. I.D.S. Japanese Reading Course 3. Multiple-path Predictive Analysis 4. Sentence-for-sentence Analyser 5. English Output 6. Other Language Pairs 7. Japanese Script I/O 8. Automatic Integrated Dictionary Compiler 9. Automatic Integrated Dictionary 10. Man-aided Translating Machine 11. Japanese-English Teaching Machine 12. Japanese-English Scientific & Techni...
متن کاملNoun Phrase Reference in Japanese-to-English Machine Translation
This paper shows the necessity of distinguishing different referential uses of noun phrases in machine translation. We argue that differentiating between the generic, referential and ascriptive uses of noun phrases is the minimum necessary to generate articles and number correctly when translating from Japanese to English. Heuristics for determining these differences are proposed for a Japanese...
متن کاملClassifiers in Japanese-to-English Machine Translation
This paper proposes an analysis of classifiers into four major types: unit, metric, group and species, based on properties of both Japanese and English. The analysis makes possible a uniform and straightforward treatment of noun phrases headed by classifiers in Japanese-to-English machine translation, and has been implemented in the MT system ALT-J/E. Although the analysis is based on the chara...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1959