Learning Language Through Interaction
Like most modern AI technology, natural language processing systems build using machine learning techniques are amazingly effective when plentiful labeled training data exists for the task/domain of interest. Unfortunately, for broad coverage (both in task and domain and language) language understanding, we're unlikely to ever have sufficient labeled data, and systems must find some other way to learn. I'll describe work we've done building methods that can learn from interactions with people. This talk highlights joint work with a number of wonderful students at collaborators at UMD, UC Boulder, UMass and MSR.