Search Results for author: Mitodru Niyogi

Found 5 papers, 0 papers with code

PARAMANU-AYN: An Efficient Novel Generative and Instruction-tuned Language Model for Indian Legal Case Documents

no code implementations20 Mar 2024 Mitodru Niyogi, Arnab Bhattacharya

We also evaluated the responses of prompts for instruction-tuned models by GPT-3. 5-Turbo on clarity, relevance, completeness, and legal reasoning metrics in a scale of 10.

Language Modelling Legal Reasoning +1

Neural Models for Source Code Synthesis and Completion

no code implementations8 Feb 2024 Mitodru Niyogi

In this master thesis, we present sequence-to-sequence deep learning models and training paradigms to map NL to general-purpose programming languages that can assist users with suggestions of source code snippets, given a NL intent, and also extend auto-completion functionality of the source code to users while they are writing source code.

Code Completion Data Augmentation +2

Paramanu: A Family of Novel Efficient Indic Generative Foundation Language Models

no code implementations31 Jan 2024 Mitodru Niyogi, Arnab Bhattacharya

It is a collection of auto-regressive monolingual, bilingual, and multilingual Indic language models pretrained from scratch on a single GPU for 10 Indian languages (Assamese, Bangla, Hindi, Konkani, Maithili, Marathi, Odia, Sanskrit, Tamil, Telugu) across 5 scripts (Bangla, Devanagari, Odia, Tamil, Telugu) of varying sizes ranging from 13. 29M to 367. 5M. The models are pretrained with a context size of 1024 on a single GPU.

Text Generation

Discovering conversational topics and emotions associated with Demonetization tweets in India

no code implementations11 Nov 2017 Mitodru Niyogi, Asim K. Pal

As one showcase, in this paper, we summarize the data set of Twitter messages related to recent demonetization of all Rs.

Cannot find the paper you are looking for? You can Submit a new open access paper.