Towards Natural Instruction based Learning

Machine Learning (ML) is traditionally formalized as the study of learning concepts from labeled examples. We are interested in providing a way for a human teacher to interact with a learner using natural instructions, thus allowing the teacher to communicate the relevant domain expertise to the learner without necessarily knowing anything about the internal representations used for learning. We introduce a learning algorithm for the instruction interpretation problem that gets feedback from its performance on the final task, while learning jointly (1) how to interpret the lesson and (2) how to use this interpretation to do well on the final task. This approach alleviates the supervision burden of traditional ML by focusing on supplying the learner with only human-level task expertise.