Translation Relations and the Combination of Analytical and Statistical Methods in Machine Translation

نویسندگان

  • Hubert Lehmann
  • Nikolaus Ott
چکیده

One of the determining factors in translation relations is semantic compatibility of cooccurring words. Methods for discovering and representing semantic compatibility relations and their role in translation relations are discussed. The methods used are a combination of analytical and statistical methods, and they are all based on an analytical model of translation. Using the case of semantic compatibility as an example, it is argued that in order to achieve progress in linguistics in general and in Machine Translation in particular neither a purely empiricist nor a purely rationalist approach will do, but that a combination of models and methods is required. Introduction The key problem of the theory of Machine Translation (MT) can be formulated as the question whether an algorithm can be devised which translates as well from one language to another as an ideal translator would. This implies that the theory of MT and its components among them a theory of verbal communication and a theory of comparing languages — must be formal theories. That such theories, if they exist, can be simply derived from observed data is an assumption apparently made by some who use statistical methods in linguistics and in particular in MT, and violently denied by Quine (1953) as well as Chomsky (1986). We advocate a pragmatist approach (as in Lehmann, 1973) which allows for abstract theoretical constructs, but we insist that they must have consequences which can be tested. We prefer operational definitions which can be implemented in algorithms used to analyze and generate texts. A key question of the theory of translation is how can we decide whether an utterance in one language is a translation of an utterance in another language, or, since we should admit that translations cannot always be perfect, whether it is a good translation of an utterance in another language. According to Quine (1959) translation amounts to a semantic correlation of sentences. In a realistic theory of translation we must be interested in larger as well as smaller linguistic

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A 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 کامل

The 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 کامل

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 کامل

A 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 کامل

بهبود و توسعه یک سیستم مترجم‌یار انگلیسی به فارسی

In recent years, significant improvements have been achieved in statistical machine translation (SMT), but still even the best machine translation technology is far from replacing or even competing with human translators. Another way to increase the productivity of the translation process is computer-assisted translation (CAT) system. In a CAT system, the human translator begins to type the tra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005