Semantic Models for Question Answering

My PhD thesis


This is my PhD thesis about the use of different semantic models in different question answering tasks.
It begins with a description of my question answering framework and its architecture.
Then I describe a large scale experiments on Yahoo Answers datasets that i carried out during my internship at Yahoo Labs in Barcelona. I used a combination of learning to rank algorithms and a big number of hand crafted features and show how distributional semantic models can replace most of them.
Finally I talk about how I built a agent that plays "Who Wants to Be a Millionaire?" using these machine learning and natural language processing techniques.

Thesis
Presentation