Mihir's repositories
In-BoXBART
In-BoXBART: Get Instructions into Biomedical Multi-task Learning
LogicBench
LogicBench is a natural language question-answering dataset consisting of 25 different reasoning patterns spanning over propositional, first-order, and non-monotonic logics.
whisper-to-speech
The aim of this project is to make voice assistants more responsive towards whisper to some extent.
dysarthric-speech-improvement
The idea behind this project is to make speech recognition more better for the people with speech pathology.
Multi-LogiEval
A comprehensive evaluation dataset encompassing multi-step logical reasoning with various inference rules and depths
asset
A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations
Extract-AI
A systematically developed human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback, offering valuable insights into how to improve coherence in extractive summaries.
genetic-algorithm
Genetic Algorithm (GA) for solving Richardson arm race model for three countries
GridPuzzle
An evaluation dataset comprising of 274 grid-based puzzles with different complexities
Logic2Text
Data and code for Logic2Text dataset
MCTACO
Dataset and code for “Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding, EMNLP 2019.
LogicAttack
This repo has all the code that is required to run the experiments for our LogicAttack Paper.
natural-instructions-expansion
Expanding natural instructions
NLP576-SIA
CLP 576 SIA Project Fall 20
open-review-toolkit
Open Review Toolkit: Better books, Higher sales, Increased access to knowledge
Speech-Pathology-Domain
Solving real life problem using Machine Learning Techniques for Speech Pathology Domain
Weak-Speech-Supervision
A first-of-its-kind system in speech domain that helps users to train state-of-the-art classification models without hand-labeling training data.