Research

I did my PhD in Automated Question Answering was at the University of Birmingham and my research focused on enabling  the creation of "intelligent" Question Answering System.

My current work continues to focus on a combination of Natural Language Processing and Deep Learning in areas such as propaganda detection and question answering.

...

Teaching

I'm currently a lecturer at the University of Birmingham School of Computer Science.

My research focuses on Natural Language Processing, Question Answering, Sentiment Analysis and Machine Cognition.

...

Entrepreneurship

Prior to starting my PhD, I co-founded and ran Webfluenz, a product based social media marketing company, for six years. Webfluenz started as a three person operation out of a small terrace in India. ...

About

My primary research interest lies in the integration of cognitive linguistics, psycholinguistics, computational linguistics and deep learning for the development of scalable, efficient, effective and understandable Natural Language Processing (NLP) systems.

My research work has centered on an interdisciplinary approach to NLP problems with an emphasis on integrating the decades of research available in both traditional NLP and cognitive linguistics with modern deep learning methods.

...

Research Highlights

Answer Selection (COLING 2018)

These are details of the system for Answer Selection that integrates fine-grained Question Classification with a Deep Learning model designed for Answer Selection. The results achieved remain the state of the art for the task and were presented at COLING 2018 in Santa Fe NM.

Data

Data associated with our work on Answer Selection which will be presented at The 27th International Conference on Computational Linguistics, Santa Fe, USA (COLING2018) can be downloaded from here (872 MB compressed). Download link: https://www.harishtayyarmadabushi.com/wp-content/uploads/coling2018data.zip

Details of the paper

C18-1278 [bib]: Harish Tayyar Madabushi; Mark Lee; John Barnden Integrating Question Classification and Deep Learning for improved Answer Selection Proceedings of the 27th International Conference on [Remains State of the Art in Answer Selection]