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

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

URL to paper listed on conference site

Bibliographic Details
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
LEADER 02090 am a22003013u 4500
001 62213
042 |a dc 
100 1 0 |a Branavan, Satchuthanan R.  |e author 
100 1 0 |a Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory  |e contributor 
100 1 0 |a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science  |e contributor 
100 1 0 |a Barzilay, Regina  |e contributor 
100 1 0 |a Barzilay, Regina  |e contributor 
100 1 0 |a Branavan, Satchuthanan R.  |e contributor 
100 1 0 |a Zettlemoyer, Luke S.  |e contributor 
700 1 0 |a Zettlemoyer, Luke S.  |e author 
700 1 0 |a Barzilay, Regina  |e author 
245 0 0 |a Reading Between the Lines: Learning to Map High-level Instructions to Commands 
260 |b Association for Computational Linguistics,   |c 2011-04-14T20:55:38Z. 
856 |z Get fulltext  |u http://hdl.handle.net/1721.1/62213 
520 |a URL to paper listed on conference site 
520 |a 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. 
520 |a National Science Foundation (U.S.) (CAREER grant IIS-0448168) 
520 |a National Science Foundation (U.S.) (grant IIS- 0835445) 
520 |a National Science Foundation (U.S.) (grant IIS-0835652) 
520 |a Microsoft Research (Fellowship) 
546 |a en_US 
655 7 |a Article 
773 |t 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 

Similar Items