Entry Date:
January 26, 2016

Grounded Question Answering


We have constructed techniques for describing videos with natural language sentences. Building on this work, we are going beyond description to answering questions such as: What is the person on the left doing with the blue object? This work takes as input a natural-language question and produces a natural-language answer.

We are striving to create an approach that will make it possible for a system to understand and answer a variety of questions, rather than constructing individual systems for each question type (who is there?, what are they doing?, where are they?, etc.).