A Punjabi to English machine translation system for legal documents

Abstract

Machine Translation (MT), also known as ?automatic translation? or ?mechanical translation?, is the computerized method that automates all or part of the process of translating from one human language to another. This research work is an attempt to build a system to translate simple sentences in legal domain from Punjabi to English. The need of the system arises from the translations of the legal documents transferred from District Courts of Punjab to the High Court in Chandigarh. The FIR which is written in Punjabi is translated to English before presenting it to the high court. To the best of my knowledge, no Machine Translation System is being developed from Punjabi to English in legal domain. It has been found through literature survey that the quality of many MT systems is low, and probably no existing system can produce completely accurate translations. However, this does not make MT useless. The process of translating a document is generally divided into two stages. The first stage is to produce a draft translation, which may not be necessarily perfect. It is then revised either by the same translator or by another translator with a view to improve the previous translation. Thus, the aim of MT is only to automate the first draft translation process and to make the overall translation process fast, simple and cheaper.[5] Since both the languages are different word order languages and have number of divergent patterns, the indirect approach is best suited approach for such type of translations. This approach broadly classifies the system into three phases, Analysis Phase, Translation Phase and the Generation Phase. The challenges in developing Punjabi to English Machine Translation System lie with major problems, mainly related to the non-availability of lexical resources, spelling variations, part of speech tagging, transliteration, named entity recognition and collocations.