My research interest lies at the intersection of machine learning and linguistics. I am largely motivated by the challenge of how machines can learn to read and understand textual data.
Everytime we describe a concept or communicate our ideas we use terms (i.e. words or phrases). Can we develop algorithms to automatically discover and learn representations of terms across domains (i.e. scientific literature, social media, newswires, etc)? Furthermore, how do we represent larger structures of meaning (e.g. sentences as composition of terms)?
These are the main questions I would like to answer in my research. This will have an impact in many natural language processing tasks such as summarisation, question-answering, recognizing entailment, etc.
2017 June 25 - July 5. Deep Learning and Reinforcement Summer School @ Montreal. Attended the summer school and I learned quite a lot. Here’s my personal write-up about it.
2016 December 8 -12. COLING paper @ Osaka. Presented my NER shared task paper. The task consists of identification of named-entities in a tweet and classification of its entity type (e.g. location, person, organisation, etc). [paper].