Target word selection in English to Persian translation using unsupervised approach

Abstract

This article studies different aspect of a new approach for resolving the problem of target word selection which can be used in machine translation systems. It uses a bilingual dictionary to find all possible translations of each word and then chooses the most appropriate alternative regarding the statistical information. A semantic dependency graph of different senses of word is generated and several ranking on nodes and edges of the graph are used to select the proper sense. Two different evaluation tasks named All-words and lexical-sample are run, which show the considerable improvements over other WSD methods on English to Persian translation system.