C-DAC Logo
 

An Interpretable Unified Framework for Text-to-Text Translation among Indian Languages using Sanskrit-based Interlingual Representation

The project proposes to use aninterlingua framework rooted on the traditional grammatical system of Sanskrit. The project will focus on Hindi, Sanskrit and Kannada as a representative subset of the Indian languages such that any observations and research innovations catering to one or more of these languages wouldbenefit other languages. Towards this primary objective of text to text translation, the project will have the following sub-objectives:

  • Develop an explainable interlingua interpreter that can capture linguistic characteristics of the languages considered under the framework and facilitate translation among these languages
  • Develop a text-to-text (T2T) translation module for translation among text in different languages and the interlingua structure
  • Human benchmarking of explainability and linguistic correctness of interlingua as a post-hoc explainer.

Use Cases

Linguistically faithful and interpretable translation system for the translation of text among multiple Indian languages.

Chief Investigator Details

Mr. Annarao Kulkarni
kulkarni@cdac.in

Top