Shikhar Murty's repositories
Question-Answering
TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.
Hierarchical-Typing
Code and Data for all experiments from our ACL 2018 paper "Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking"
Pushdown-Layers
Code for Pushdown Layers from our EMNLP 2023 paper
structural-grokking
Code for our ACL '23 paper titled "Grokking of Hierarchical Structure in Vanilla Transformers"
LanguagePatching
Code for our EMNLP '22 paper "Fixing Model Bugs with Natural Language Patches"
TreeProjections
Tool to measure tree-structuredness of the internal algorithm learnt by a transformer
google-interview-university
A complete daily plan for studying to become a Google software engineer.
Algorithms
Quick and dirty code for Sport programming/Interview problems.
Natural-Language-Processing
Course projects for NLP (COL772) - Spring 2016
Distributed-VecXMat
A nifty piece of code for Multiplying a huge sparse matrix with a vector using the power of GPUs and distributed computing
expressivo
A symbolic differentiation engine for Polynomials
GraphicalModels
Implementation of Graphical models along with inference and learning in a series of 3 assignments
machine-learning-for-software-engineers
A complete daily plan for studying to become a machine learning engineer.
MurtyShikhar.github.io
Personal Website
neural-symbolic-machines
Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.
tufte-jekyll-trial
Minimal Jekyll blog styled to resemble the look and layout of Edward Tufte's books
website-2
Trial website 2
website-new
New website trial