English to Indian Language Machine Translation System

Brief Description

EILMT project has the facility of translation from English to eight Indian languages; namely, Hindi, Bengali, Marathi, Urdu, Tamil, Oriya, Gujarati and Bodo in Tourism and Health domain. C-DAC-Pune is the consortium leader in association with 12 institutes, namely, IIIT-Hyderabad, C-DAC-Mumbai, IIT-Bombay, Jadavpur University, IIIT-Allahabad, Utkal University-Bhubaneswar, Amrita University-Coimbatore, BanasthaliVidhyapeeth, North Maharashtra University-Jalgaon, Dharamsinh Desai University - Nadiad and North Eastern Hill University - Shillong.

Main uses and domain

Machine Translation from English to Eight Indian Languages pertaining to domains - Tourism and Health

Features and Technical Specifications

Being Consortia mode project, EILMT has been designed to work with the platform and technology independent modules. It is facilitated with the Hybrid Architecture of thin-client/thick-server design, where it uses four engines in parallel to provide best translation output. There are various approaches like web services, http protocols and standard web browsers are available for users (clients) to communicate with the translation services of the server.

Translation Engines used here are TAG based MT (Parser and Generator) and Statistical MT (SMT). The basic tools, such as, Input Format Extractor, Morph Analyzer & synthesizer, Named Entity Recognizer, POS Tagger, Word Sense Disambiguator, Semantic TAG Parser, Post Processing Tools, Linguistic Resource Management Tools and multilingual evaluation methodologies & Ranking Module are used.

System is facilitated with features such as -

  • The System is designed to use three-translation engines (EBMT, SMT & TAG) working in parallel, which facilitate the translation for all the eight language pairs.
  • The Collation & Ranking Module is responsible for collating translated outputs of all the 03 engines for a given language pair and rank them on the basis of translation accuracy.
  • Direct Data Capture Facility for device integration
  • System is compatible with W3C Consortium Guidelines
  • Browser compatibility is provided for popular browsers such as Google Chrome, Mozilla Firefox, Internet Explorer, Opera and Apple Safari.
  • User Log module with
    • User friendly Graphical User Interface (GUI)
    • New-User Registration Module
    • The user can either upload and edit a file/document or type directly into the text area of the system, for translation
  • Pre-Processing module that prepares input text into engine suitable form with the help of
    • Input Format Extractor for extracting text from uploaded files and translating for the formats .rtf, .xls, .txt and .html
    • Morphological Analyzer
    • Part of Speech Tagger
    • Named Entity Recognizer including Name, Place, Date
    • Word Sense Disambiguator
    • Noun/ Phrase Chunking, Clause Identification
  • Post processing module provides additional features for EILMT Translation engine like
    • Morph Synthesizer for smoothening the translated output
    • Multiple translation options
    • Synonym selection option
    • Typing facility for Target Languages
    • Transliteration Facility
    • Retaining the original format of English text

Platform required(if any)


Read more     Download Brochure

Contact Details for Techno Commercial Information

C-DAC Pune, AAI Group
4th Floor, CDAC Innovation Park,
Panchwati Pashan , Pune - 411 008
Phone No. : 020-25503335/255033305
Email: info[dot]aai[at]cdac[dot]in