Tayebeh Mosavi Miangah 1
Abstract In recent years, queen-size monolingual, comparable and parallel corpora have played a in truth crucial role in solving various problems of computational linguistics including machine rendering, breeding convalescence, natural language processing, and the like. This newsprint tries to solve the problem of polysemy of Persian backchats season translating them into Persian by the computer. We use Mutual Information statistics obtained from a very large monolingual corpus of Persian. Mutual information values are work out based on backup frequencies of words and used to measure the correlation between words. utilize mutual information statistics the occurrence or co-occurrence frequencies of diverse equivalents of an ambiguous word in the tar part language is calculated and the most probable equivalent for every ambiguous word is selected. When mutual information value is high, the word associations are industrial-strength and provide dependable results for translational disambiguation and vice versa.
The method discussed in this paper not only prat be straightway applied in the system of Persian-English machine translation, but excessively it can certainly increase performance effectiveness of the retrieval tasks, especially in cross-language information retrieval. 1. Introduction Automatic translation of texts from one language into another one faces various problems among which we can name lexical ambiguity. Lexical ambiguity refers to a slick in which either a lexical unit belongs to various part-of-speech categories with different senses, or to a lexical unit for which in that respect is more than one sense, while these different senses fall into the similar part-of-speech category (Mosavi Miangah, 2000). Our concern in this study is solving the atomic number 42 type of lexical ambiguity, that is, those lexical ambiguities in which the different senses of a word fall into the same lexical category....If you want to get a full essay, order it on our website: Orderessay
If you want to get a full essay, wisit our page: write my essay .
No comments:
Post a Comment