Progress in machine translation
نویسنده
چکیده
IT is now twelve years since I tentatively suggested that it should be possible to translate a foreign language by means of a digital computer. During this period many people have started to work on the idea, and we have now reached a stage when at least in theory it would be possible to set about building a special purpose translating machine. It may be interesting, therefore, to survey how tar we have progressed and to venture a prediction about the future. In order to do so we have to be quite clear what is meant by a translation: there are two possible levels of definition. First, we could say that the process of translation consists in replacing a set of words in one language— the "source" language—by another set of words in a second language—the "target" language—the latter set expressing not only the meaning but also the intention of the original author. The inclusion of intention covers the possibility of replacing, say, poetry in one language by poetry in another. The other, and less demanding, definition of translation would require only that the second set of words should reproduce the ideas contained in the original language, but should not attempt to reproduce the stylistic intentions of the original writer. It must be explained at once that the mechanical realisation of a high quality translation conveying intention as well as meaning is still very far away. You may be wondering how a computing machine designed to work with numbers can be used to translate words. The answer is quite simple. The letters of the alphabet in the source language or languages from which the machine is required to translate are "coded " in numerical form. For example, we might use the numerals 01 to represent A, 02 to represent B, 03 to represent C, and so on throughout the alphabet. A word is then represented by a string of numbers, each number being the code equivalent for the letter. Thus the word "translation" would be represented by the numbers 20 18 01 14 19 12 01 20 09 15 14 T R A N S L A T I O N In its simplest form, translating, or more properly transcribing, by a human being consists merely of looking up meanings of the word of the source language in a dictionary and finding its equivalent in the target language. This is precisely the same process as looking up the logarithm of a number or the sine of an angle in a mathematical table. It would not require an extremely complex machine to perform this function, provided that the machine contained somewhere inside it all the information contained in a dictionary.
منابع مشابه
A Comparative Study of English-Persian Translation of Neural Google Translation
Many studies abroad have focused on neural machine translation and almost all concluded that this method was much closer to humanistic translation than machine translation. Therefore, this paper aimed at investigating whether neural machine translation was more acceptable in English-Persian translation in comparison with machine translation. Hence, two types of text were chosen to be translated...
متن کاملThe Correlation of Machine Translation Evaluation Metrics with Human Judgement on Persian Language
Machine Translation Evaluation Metrics (MTEMs) are the central core of Machine Translation (MT) engines as they are developed based on frequent evaluation. Although MTEMs are widespread today, their validity and quality for many languages is still under question. The aim of this research study was to examine the validity and assess the quality of MTEMs from Lexical Similarity set on machine tra...
متن کاملA new model for persian multi-part words edition based on statistical machine translation
Multi-part words in English language are hyphenated and hyphen is used to separate different parts. Persian language consists of multi-part words as well. Based on Persian morphology, half-space character is needed to separate parts of multi-part words where in many cases people incorrectly use space character instead of half-space character. This common incorrectly use of space leads to some s...
متن کاملA Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملStatistical Sign Language Translation
Abstract In the field of machine translation, significant progress has been made by using statistical methods. In this paper we suggest a statistical machine translation system for Sign Language and written language, especially for the language pair German Sign Language (DGS) and German. After introducing the system’s architecture, statistical machine translation in general and notation systems...
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 2012