Reading Between the Lines: Learning to Map High-level Instructions to Commands

• Main Authors: Branavan, Satchuthanan R. (Contributor), Zettlemoyer, Luke S. (Contributor), Barzilay, Regina (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Association for Computational Linguistics, 2011-04-14T20:55:38Z.
• Subjects: Article
• Online Access: Get fulltext

URL to paper listed on conference site
In this paper, we address the task of mapping high-level instructions to commands in an external environment. Processing these instructions is challenging-they posit goals to be achieved without specifying the steps required to complete them. We describe a method that fills in missing information using an automatically derived environment model that encodes states, transitions, and commands that cause these transitions to happen. We present an efficient approximate approach for learning this environment model as part of a policy-gradient reinforcement learning algorithm for text interpretation. This design enables learning for mapping high-level instructions, which previous statistical methods cannot handle.
National Science Foundation (U.S.) (CAREER grant IIS-0448168)
National Science Foundation (U.S.) (grant IIS- 0835445)
National Science Foundation (U.S.) (grant IIS-0835652)
Microsoft Research (Fellowship)