Research

Research Summary:

The goal of my research is to understand the meaning in text and speech (semantic analysis), in order to automatically generate language that is fluent and appropriate to the context. This involves observing statistical patterns of language use, and then developing algorithms that can automatically reason with these statistically derived meaning representations. The reasoning and inference component can then be used in language generation applications.

What impact does your research have?

Designing systems that are able to understand and generate language is crucial to allowing users to interact with them naturally. Some existing examples include news summarization systems, personal assistant apps, and natural language search such as Facebook’s graph search. But this is just the beginning—language understanding and generation will find new applications in areas such as games, educational software, and many others.

How did the Facebook Fellowship help support this?

The Facebook Fellowship allowed me to focus on my research without worrying about funding. It has also allowed me to attend academic conferences to talk with leading researchers about my work, which I otherwise would not have been able to do. Overall, it has given me a great boost to my career!

How was the experience of being a Facebook Fellow?

One of the best parts of the fellowship is that it gives you the opportunity to visit the Facebook campus and present your work to Facebook engineers and research scientists. Getting their feedback and learning about the problems that they are working on was exciting and illuminating.

What are the next steps for you in your research?

I am finishing up the last steps of my PhD, and will begin a faculty position at McGill University in Montreal. I am excited to be starting my own research group that can pursue research directions in semantics and natural language generation!