Krishna Chaitanya Sanagavarapu

Toronto, ON, Canada · +1 (940) 222-1277 · krishnacsanagavarapu@gmail.com

I recently worked as a Sr. Applied Research Scientist at ServiceNow. My research interests are Machine Learning, Natural Language Understanding and Generation. I have 5+ years of professional experience in Analysis, Design, Development, Implementation, and testing of various stand-alone and client-server architecture-based enterprise application software in python.

My favourite movie character is Batman and favourite movie director is Christopher Nolan. I like photography and travelling. Scroll down to know more about me and do connect to me on...

Experience

Sr. Applied Research Scientist

ServiceNow
March 2022 - June 2022

Research Assistant for Dr. Eduardo Blanco

University of North Texas, Arizona State University
January 2021 - December 2021

Language Engineer

Apple

Improve the user experience for SIRI in India through developing on Speech Recognition, Natural language models and customize functionality for the Indian market.

July 2019 - December 2020

Data Engineer

CBRE

Implemented Profiling, Analytics and visualizations from various sources using Python and PowerBI. Developed complex data scripts (Primarily SQL) for ETL and Data Warehousing.

May 2017 - July 2019

Software Engineer

Tech Mahindra

Synthesized various MongoDB database queries from Python using MongoEngine and PyMongo, Used Pandas library for Statistical Analysis.

December 2013 - December 2015

Intern

Defense Research and Development Laboratory(DRDL)-DRDO

Developed an application where data sent from a defense application’s program to be stored and organized in an efficient manner according to the timing order received.

December 2012 - April 2013

Intern

Enlume Inc.

Created Python routines to log into the websites and fetch data for selected options. Handled business logics by backend Python programming to achieve optimal results.

January 2012 - April 2012

Education

University of North Texas

Master of Science
Computer Science - ML/NLP concentration

GPA: 3.70

December 2015 - May 2017

Aurora's Engineering College - JNTU - Hyderabad

Bachelor of Technology
Computer Science and Engineering

GPA: 3.66

August 2009 - May 2013

Skills

Programming Languages & Tools
Experience
  • Machine Learning
  • Natural Language Understanding & Generation
  • Jupyter, PyCharm, Eclipse
  • Pandas, Numpy, Matplotlib, SciPy, Scikit-Learn, PyTorch
  • Agile Development & Scrum
  • Amazon EC2 & Amazon S3

Research Publications

  • Krishna Sanagavarapu, Jathin Singaraju, Anusha Kakileti, Anirudh Kaza, Aaron Mathews, Helen Li, Nathan Brito, and Eduardo Blanco. 2022. Disentangling Indirect Answers to Yes-No Questions in Real Conversations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4677–4695, Seattle, United States. Association for Computational Linguistics. (NAACL) | pdf
  • Krishna C Sanagavarapu, Alakananda Vempala and Eduardo Blanco. 2017. Determining When and Whether People Participate in The Events They Tweet About. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada | pdf
  • Sanagavarapu, Krishna Chaitanya. Determining Whether and When People Participate in the Events They Tweet About, Master’s thesis, May 2017; University of North Texas, Denton, Texas | pdf

Projects

Bike Sharing

we've built a neural network and use it to predict daily bike rental ridership. (Source code)

Dog Breed Classifier

In this project, given an image of a dog, this algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.(Source code)

Face Generation

This project defines and trains a DCGAN on a dataset of faces. The goal is to get a generator network to generate new images of faces that look as realistic as possible.(Source code)

TV script generation

This project generates our own Seinfeld TV scripts using RNNs. Used part of the Seinfeld dataset of scripts from 9 seasons. The Neural Network built will generate a new ,"fake" TV script, based on patterns it recognizes in this training data.(Source code)

Sentiment Analysis - Sagemaker

Our goal will be to have a simple web page which a user can use to enter a movie review. The web page will then send the review off to our deployed model which will predict the sentiment of the entered review.(Source code)