My research focuses on the computational foundations of intelligent behavior, through the lens of natural language. I mostly identify with natural language processing (ACL, NAACL, EMNLP) and artificial intelligence communities (AAAI, IJCAI) and, to some extent, with the machine learning community (NourIPS, ICML).
My goal is to explore the different ways in which we can develop and evaluate systems that understand and reason with (and about) natural language in different contexts. My thesis focused on different analyses related to construction of knowledge-aware language comprehension systems that can make effective use of background information from different sources. Parts of my work focused on the Science Exam challenges of the Aristo project (IJCAI 16). Just earlier this year, Aristo reached its milestone by achieving over 90% in Science 8th grade – a milestone for AI and NLP.
I tend to worry a lot about the unintended consequences of technology in all areas of our lives. These include, but are not limited to, algorithmic biases, echo chambers in digital spaces, and the contamination of information gateways. More recently, in an effort to mitigate the effect of echo-chambers, we explore ways to organize ideas about controversial issues in ways that allows people to see alternative views and help them have a more open mindset (NAACL 19).