Abhirut Gupta

Research Software Engineer
IBM Research
Email: abhirutgupta@in.ibm.com

I am a Research Engineer at IBM Research, Bangalore, and I work on automating technical support. Currently, I am working on building systems to understand complex technical support questions. Only around 19% of questions in technical support are simple "factoid". Around 50% questions require complex understanding of the problem, the setup which led to the problem, and attempts by the user to mitigate it. I am also fascinated by "humor" in natural language and am exploring algorithms that can "understand" humor in text and eventually even create it.


Research Interest

My research interest lies in exploring application of machine learning techniques to open problems in Natural Language Processing. Areas of interest include Natural Language Processing, Information Extraction, Information Retrieval, and Machine Learning.

In particular, I would like to explore techniques for understanding unstructured information like language or images with limited supervision.



  1. Abhirut Gupta, Abhay Khosla, Gautam Singh, Gargi Dasgupta. Mining Procedures from Technical Support Documents. arXiv preprint arXiv:1805.09780
  2. Abhirut Gupta, Anupama Ray, Gautam Singh, Gargi Dasgupta, Pooja Aggarwal, and Prateeti Mohapatra. Semantic Parsing for Technical Support Questions. Set to appear in COLING 2018

  3. 2016

  4. Abhirut Gupta, Arjun Akula, Gargi Dasgupta, Pooja Aggarwal, and Prateeti Mohapatra. Desire: Deep Semantic Understanding and Retrieval for Technical Support Services. ICSOC 2016 Workshops. PDF


  1. System and Method for Instance Specific Aspect Based Cross Documents Sentiment Aggregation. Application Number 14/937551
  2. Deep Learning based Unsupervised Event Learning for Economic Indicator Prediction. Application Number 15/258176