Papers by Priyanka Bedekar

1 papers
Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users (2023.findings-emnlp)

Copied to clipboard

Challenge: Indian subcontinent is home to diverse languages written in multiple scripts . widespread use of romanization and lack of standardization means accurate transliteration models form a critical component in the NLP stack for Indian languages used by over 735 million Internet users.
Approach: They propose to build a transliteration dataset using monolingual and parallel corpora and human annotators.
Outcome: The proposed model improves accuracy by 15% on the Dakshina test set and establishes strong baselines on the Aksharantar test set.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations