Notice (17th Nov 2024): Thank you for visiting! To stay updated with my latest professional endeavours and connect directly, I invite you to find me on LinkedIn (link), where I maintain an active presence. In the grand tradition of personal websites everywhere, this one has gracefully retired from active duty.

I am Keshav, a PhD candidate at Indian Insitute of Technology (IIT), Delhi. I work in the broad area of Natural Language Processing (NLP) and Deep Learning. I am fortunate to be jointly advised by Prof. Mausam (HoD, School of AI, IIT Delhi) and Prof. Soumen Chakrabarti (IIT Bombay). In my PhD research (published at ACL and EMNLP), I worked on building cutting-edge Open Information Extraction (OpenIE) systems. OpenIE has wide industry-use, being a leading technique for constructing large-scale KBs across a vareity of domains, ranging from finance to medicine. Our open-sourced models have been downloaded more than 5K+ times.

I am very motivated about building NLP technology for Indian languages. Software has crept into every part of modern life, making it seemingly impossible to escape from it. In the current scenario, removing barriers of entry is critical for larger sections of the society to adapt to this rapidly changing environment. Language remains an important barrier in an Indian context which is known for its many tongues. I am interested in using my knowledge of NLP to play a role in bridging this gap. I had the chance to kick-start my contributions towards this goal as a Visiting Student Researcher at Google Research, Bangalore (Spring, 2020), where I worked with Partha Talukdar, Martin Rezk, Pat Verga and William Cohen on linking Indian text to Knowledge Bases that are predominantly English centric.

During my BTech days at IIT Bhubaneswar, I had the chance to work with Prof Chitta Baral (Arizona State University), Prof Partha Roop (University of Auckland) and Prof Manoranjan (IIT Bhubhaneswar) on a wide variety of interesting research problems in Computer Vision, Synchornous Programs and Software Testing. I also had the opportunity to work as a Research Intern at IBM Research, Delhi (Summer, 2017) where I worked on Dialogue systems and as a Data Science intern at Microsoft Bing, Hyderabad (Summer, 2016) I worked on clustering user-search queries.

I am currently on the job market. Please feel free to reach out to me over email: keshav.kolluru@gmail.com I am always on the lookout for exciting opportunitites.

Publications

1. IMoJIE: Iterative Memory-Based Joint Open Information Extraction
   Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam and Soumen Chakrabarti
   Association for Computational Linguistics (ACL), 2020.
   Paper | Code

2. OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction
   Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam and Soumen Chakrabarti
   Empirical Methods in Natural Language Processing (EMNLP), 2020.
   Paper | Code

3. Multilingual Fact Linking
   Keshav Kolluru, Martin Rezk, Pat Verga, William W. Cohen, and Partha Talukdar
   Automated Knowledge Base Construction (AKBC), 2021.
   Paper | Code

4. Consistent Crosslingual Data Transfer for Open Information Extraction
   Keshav Kolluru, Muqeeth Mohammad, Shubham Mittal, Soumen Chakrabarti and Mausam
   Under submission

5. Proper Noun Compound Interpretation
   Keshav Kolluru, Gabriel Stanovsky, and Mausam
   Under preparation.

6. CEAR: Cross Entity Aware Reranking for Open Knowledge Base Completion
   Keshav Kolluru, Mayank Kumar, Yatin Nandwani, Parag Singla and Mausam
   Under preparation.