Akshay Parakh

Akshay Parekh

PhD Student, Department of Computer Science & Engineering, IIT Guwahati

About Me

Currently, I am pursuing Ph.D under joint supervision of Dr. Ashish Anand and Dr. Amit Awekar at Indian Institute of Technology, Guwahati. Prior to joining IIT Guwahati, I earned my Bachelor in Engineeing (B.E.) degree in Computer Science & Engineering from G H Raisoni College of Engineering, Nagpur.

My research work centers around Natural Language Processing, Information Extraction & Deep Learning, mainly focusing on Large-scale Relation Extraction.

I enjoy playing Table Tennis & Footbal. I also like to travel, trek, and explore hidden places and local food. I have keen interest on Finance and Startup Industry.

Publications

  1. Akshay Parekh, Ashish Anand, Amit Awekar. Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases. Proceedings of the 7th ACM IKDD CoDS and 25th COMAD.[paper] [resource]
  2. Balaji Ganesan, Riddhiman Dasgupta, Akshay Parekh, Hima Patel, Berthold Reinwald. A Neural Architecture for Person Ontology Population.[paper]

Academic Work Experience

Research Scholar - Department of Computer Science and Engineering, Indian Institute of Technology, Guwahti (2016 - Present)

  • TA - (CS110)Programming Language Lab
  • TA - (CS210)Data Structure Lab
  • TA - (CS565)Intelligent System and Interfaces
  • TA - (CS242)System Software Lab
  • TA - (CS595)Data Visualization
  • TA - (CS203/CS204)Data Structure and Algorithms

Industry Work Experience

Research Intern - IBM Research Labs, Bangalore (May 2019 - Aug 2019)

Relation Extraction, Ontology Creation, Natural Language Processing, Deep Learning

Startup Work Experience

Software Developer - Shopista - Digitales Communication Pvt. Ltd. (Jan 2015 - June 2015)

Android Application UI Designer, Web Scraping & Information Extraction.

Projects

Relation Extraction for Ontology Creation.

Internship project at IBM Reasearch Labs, Bangalore. In this project, we developed an end-to-end model to extract relations between real-world entities from texts for ontology creation. We based our model on On2vec and used TACRED and other industry datasets for evaluation.

Generating Knowledge Graph from wikipedia infobox

This is part of my initial work for my PhD thesis work. In this project, I extract all the infobox from the Wikipedia xml dump. Categorize infobox template types in Person, Organization, and Location. Parse all the infobox that falls into one of the category. Also generate list of relations for each of the 3 types. Finally, extract information in the form of triple (e1, r, e2)

View on GitHub

Packet Filtering Filrewall for Linux Kernel

Course project for DSSD, developed in C/C++ using iptables, netfileters and Linux Kernel module.

Lectures/Talks

Hands-on Session on Deep Learning - Workshop: AI for Healthcare, IIT Guwahati (2019).

Lecture on Python basics - CS 224, IIT Guwahati (Fall 2019). [Lecture Resource]

Hands-on Session on Python for Machine Learning RSF, EEE, IIT Guwahati (16 November 2019). [Github Repo]

Hands-on Session on Introduction to Tensorflow==1.x TEQIP: DL for NLP, IIT Guwahati (19 November 2019). [Colab Notebook] [Resource]

Hands-on Session on Introduction to Python for Data Analysis and Text Processing Management Development Programme on AI in its possible implementation in Indian context., IIT Guwahati (20 November 2019). [Colab Notebook] [Resource]