Ministry of Education
Researchers at IIT Kharagpur Develop Digital Infrastructure for Efficient Processing of Sanskrit Texts for Making the Language Accessible
Posted On: 25 MAR 2021 5:51PM
Feature
*Srijata Saha Sahoo
The Astadhyayi (eight chapters) composed by Panini within the 6th – 5th century BCE remains to be thought of as a wealthy commentatorial literature although the origin of the language is traced again to the twond millennium BCE when the Rig Veda was written after being continued for hundreds of years by means of oral custom and preservation of verbal information within the guru-disciple relationship.
After a few years of stagnation, there was a renewed curiosity in Sanskrit for the reason that announcement of NEP 2020. Besides, it needs to be talked about additionally that most of the phrases in English have their origin in Sanskrit, like ‘Path’ from ‘Patha’, ‘Man’ from ‘Manu’, ‘Door’ from ‘Dwar’ and the like.
Various tutorial establishments each in school training in addition to larger training are adopting innumerable approaches for enhancing the attain of the language by means of coaching programmes, analysis and outreach initiatives. While numerous digital sources have improved the accessibility and use of world languages in addition to regional languages, Sanskrit presents distinctive challenges in automated computational processing.
This aside, to the sheer quantity and variety, each stylistic and chronological, present in Sanskrit texts, the linguistic peculiarities expressed by the language; pose a number of challenges in making these works accessible to the world.
To tackle such jeopardy, researchers at IIT Kharagpur led by Dr. Pawan Goyal have developed a digital infrastructure for the environment friendly processing of Sanskrit texts, by successfully combining state-of-the-art machine studying strategies and conventional linguistic information from Sanskrit. The proposed framework relies on energy-based fashions and it permits the encoding of related linguistic data as constraints. In the phrases of Dr. Goyal, “Processing of Sanskrit texts poses several challenges owing to the high lexical productivity of the words, free word order in poetry, euphonic assimilation of sounds at the word boundaries and phonemic orthography followed in writing. Keeping these in mind, we proposed a generic graph-based framework that takes advantage of the free word order nature of the language. Further, we made use of linguistic insights from the traditional Sanskrit grammar for learning the feature function and applying the relevant constraints.” He additional added, “Our proposed framework substantially reduced the training data requirements to as low as 10%, as compared to that of the neural state-of-the-art models. In all the Sanskrit-related tasks discussed in the work, we either achieved state-of-the-art results or ours is the only data-driven solution for those tasks,”
This work is accepted for publication within the Computational Linguistics journal revealed by the MIT Press. This work has been carried by analysis scholar Dr. Amrith Krishna, at the moment a post-doc on the University of Cambridge, supervised by Dr. Pawan Goyal. The paper at the moment addresses the duties of phrase segmentation, morphological parsing, dependency parsing and poetry to prose conversion of Sanskrit textual content. The crew is now actively collaborating with a number of exterior analysis teams to increase the appliance of the proposed system for automated speech recognition and question-answering in Sanskrit.
Works in Sanskrit, numbering greater than 30 million extant manuscripts, embody in depth epics, delicate and complex philosophical, mathematical, and scientific treatises, and wealthy literary, poetic, and dramatic texts. The proposed AI-based system, used along with interactive instruments such because the Sanskrit Heritage reader, might assist the customers within the simpler evaluation of those manuscripts with word-by-word evaluation and translation, the relation between phrases, poetry to prose conversion, search and query answering, and many others.
Let us hope that from now onwards Sanskrit transforms to a extra simply obtainable language to its connoisseurs.
***
SSS
(Features ID: 150741)
0
