E-Dictionary



Resource Center for Indian Language Technology Solution – Oriya

DIT, MCIT, Govt. of India

Department of Computer Science and Application,

Utkal University, Bhubaneswar,

Orissa-751004

I) Oriya Machine Translation (OMT):

➢ A prototype for translation of English to Oriya language.

➢ Working unambiguously for simple sentences.

➢ Designed on the principles of object-oriented approach.

➢ Parser of OMT system is efficient enough to be used in the translation of English to other Indian languages.

➢ Word sense disambiguation is done using N-gram model.

➢ Got IPR.

(II) Speech Processing (SP):

(A) Text To Speech (TTS) System:

➢ Speech synthesizer for Oriya language is

designed by the character based

concatenation technique.

➢ The transition between two characters is stored by taking the help of Paninian philology to give a natural shape to the output.

➢ In addition to Oriya language we are in the process of developing a TTS system for Hindi in syllable base concatenation

➢ Got IPR & Tested by SQTC, ETDC Banglore

(B) Speech To Text (STT) system:

➢ Recognising words, designed through a training process of phones, diphones and triphones.

➢ Telephone directory system based on Oriya character recognition system.

➢ Applied for IPR.

(III) Knowledge Management:

(A)Optical Character Recognition (OCR):

➢ Converts scanned content to text

➢ An OCR with TTS - DIVYADRUSTI,

➢ User - Press, Media & Educational Institutes

➢ Operates in command mode so useful for Illiterate and Visually Challenged.

➢ Got IPR & Tested by SQTC, ETDC Banglore.

(B) English Reader System

➢ Uses English OCR System

➢ Integrated with Microsoft Text To Speech Engine.

➢ Also integrated with Microsoft Speech To Text Engine to operate in command mode.

(III) Lexical Resources

A) e-Dictionary (Oriya (English(Hindi) – Got IPR. and Tested by SQTC, ETDC Banglore 27,000 Oriya, 30,000 English and 20,000 Hindi words.

(B) Oriya WordNet with Morphological

Analyzer. Got IPR. , Tested by SQTC, ETDC

Banglore -1,000 Lexicon.

(C) Ori-Spell (Oriya Spell Checker) – Got IPR ,

Tested by SQTC, ETDC Banglore, 1,70,000

words (root and derived).

(D) Trilingual Word Processor (Hindi-

English-Oriya)

Integrated with Spell Checker and Grammar

Checker.

(F) San-Net (Sanskrit Word-Net)

➢ Developed using Navya-NyAya (xÉ´ªÉxªÉɪÉ) Philosophy and Paninian Grammar.

➢ Besides Synonymy, Antonym, Hypernym, Hyponym, Holonym and Meronyms etc., some more relation such as: Analogy, Etymology, Definition, Nominal Verb, Nominal Qualifier, Verbal Qualifier and Verbal Noun have been introduced in San-Net.

➢ San-Net can be used for Indian language understanding, translating, summarizing and generating.

➢ A standard Knowledge Base (KB) has been developed for analyzing syntactic, semantic and pragmatic aspects of any lexicon.

(IV) New Initiatives:

OCR - Hand Written Character Recognition

Speech – ASR & Speech Corpora

LR – MT using Sanskrit WordNet as base

Contact

Dr. (Mrs) Sanghamitra Mohanty

Chief Investigator

RC-ILTS-ORIYA, Dept. of Computer Science & Application, Utkal University, Bhubaneswar, Orissa – 751004

Ph: 0674-2585518(L)/2580216 (O)

Email: sangham1@

sangham1@sancharnet.in

Website: ilts-

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download