Reading Between the Lines: Learning to Map High-level Instructions to Commands
Author(s)Branavan, Satchuthanan R.; Zettlemoyer, Luke S.; Barzilay, Regina
DownloadBarzilay_Reading between.pdf (414.5Kb)
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
MetadataShow full item record
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.
URL to paper listed on conference site
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
Association for Computational Linguistics
Branavan, S.R.K., Luke S. Zettlemoyer, Regina Barzilay. "Reading Between the Lines: Learning to Map High-level Instructions to Commands." 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, July 11–16, 2010.
Author's final manuscript