acl acl2013 acl2013-230 acl2013-230-reference knowledge-graph by maker-knowledge-mining

230 acl-2013-Lightly Supervised Learning of Procedural Dialog Systems


Source: pdf

Author: Svitlana Volkova ; Pallavi Choudhury ; Chris Quirk ; Bill Dolan ; Luke Zettlemoyer

Abstract: Procedural dialog systems can help users achieve a wide range of goals. However, such systems are challenging to build, currently requiring manual engineering of substantial domain-specific task knowledge and dialog management strategies. In this paper, we demonstrate that it is possible to learn procedural dialog systems given only light supervision, of the type that can be provided by non-experts. We consider domains where the required task knowledge exists in textual form (e.g., instructional web pages) and where system builders have access to statements of user intent (e.g., search query logs or dialog interactions). To learn from such textual resources, we describe a novel approach that first automatically extracts task knowledge from instructions, then learns a dialog manager over this task knowledge to provide assistance. Evaluation in a Microsoft Office domain shows that the individual components are highly accurate and can be integrated into a dialog system that provides effective help to users.


reference text

Priti Aggarwal, Ron Artstein, Jillian Gerten, Anthanasios Katsamanis, Shrikanth Narayanan, Angela Nazarian, and David R. Traum. 2012. The twins corpus of museum visitor questions. In Proceedings of LREC. Yoav Artzi and Luke Zettlemoyer. 2011. Learning to recover meaning from unannotated conversational interactions. In NIPS Workshop In Learning Semantics. Yoav Artzi and Luke Zettlemoyer. 2013. Weakly supervised learning of semantic parsers for mapping instructions to actions. Transactions of the Association for Computational Linguistics, 1(1):49–62. Michael S. Bernstein, Greg Little, Robert C. Miller, Bj¨ orn Hartmann, Mark S. Ackerman, David R. Karger, David Crowell, and Katrina Panovich. 2010. Soylent: a word processor with a crowd inside. In Proceedings of ACM Symposium on User Interface Software and Technology. 1677 S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer, and Regina Barzilay. 2009. Reinforcement learning for mapping instructions to actions. In Proceedings of ACL. S. R. K. Branavan, Luke S. Zettlemoyer, and Regina Barzilay. 2010. Reading between the lines: learning to map high-level instructions to commands. In Proceedings of ACL. S. R. K. Branavan, David Silver, and Regina Barzilay. 2011. Learning to win by reading manuals in a monte-carlo framework. In Proceedings of ACL. Asli Celikyilmaz and Dilek Hakkani-Tur. 2012. A joint model for discovery of aspects in utterances. In Proceedings of ACL. Asli Celikyilmaz, Dilek Hakkani-T u¨r, and Gokhan T u¨r. 2011. Mining search query logs for spoken language understanding. In Proceedings of ICML. David L. Chen and William B. Dolan. 2011. Collecting highly parallel data for paraphrase evaluation. In Proceedings of ACL. David L. Chen and Raymond J. Mooney. 2011. Learning to interpret natural language navigation instructions from observations. In Proceedings of AAAI. Myroslava Dzikovska, Amy Isard, Peter Bell, Johanna D. Moore, Natalie B. Steinhauser, Gwendolyn E. Campbell, Leanne S. Taylor, Simon Caine, and Charlie Scott. 2011. Adaptive intelligent tutorial dialogue in the beetle ii system. In Proceedings of AIED. Kallirroi Georgila, James Henderson, and Oliver Lemon. 2005. Learning user simulations for information state update dialogue systems. In Proceedings of Eurospeech. Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Ashley Fidler, and Asli Celikyilmaz. 2012. A discriminative classification-based approach to information state updates for a multi-domain dialog system. In Proceedings of Interspeech. Peter Heeman. 2007. Combining Reinforcement Learning with Information-State Update Rules. In Proceedings of ACL. Eric Horvitz, Jack Breese, David Heckerman, David Hovel, and Koos Rommelse. 1998. The Lumiere project: Bayesian user modeling for inferring the goals and needs of software users. In Proceedings of Uncertainty in Artificial Intelligence. Nate Kushman, Micah Brodsky, S. R. K. Branavan, Dina Katabi, Regina Barzilay, and Martin Rinard. 2009. WikiDo. In ACM HotNets. Cheongjae Lee, Sangkeun Jung, Kyungduk Kim, and Gary Geunbae Lee. 2009. Automatic agenda graph construction from human-human dialogs using clustering method. In Proceedings of NAACL. Xiao Li, Ye-Yi Wang, and Alex Acero. 2008. Learning query intent from regularized click graphs. In Proceedings of SIGIR. Percy Liang, Michael I. Jordan, and Dan Klein. 2009. Learning semantic correspondences with less supervision. In Proceedings of ACL-IJCNLP. F. Mairesse, M. Gasic, F. Jurcicek, S. Keizer, B. Thomson, K. Yu, and S. Young. 2009. Spoken language understanding from unaligned data using discriminative classification models. In Proceedings of Acoustics, Speech and Signal Processing. Fabrizio Morbini, Eric Forbell, David DeVault, Kenji Sagae, David R. Traum, and Albert A. Rizzo. 2012. A mixed-initiative conversational dialogue system for healthcare. In Proceedings of SIGDIAL. Jorge Nocedal and Stephen J. Wright. 2000. Numerical Optimization. Springer. Patric Pantel, Thomas Lin, and Michael Gamon. 2012. Mining entity types from query logs via user intent. In Proceedings of ACL. Paul Piwek and Svetlana Stoyanchev. 2010. Generating expository dialogue from monologue: Motivation, corpus and preliminary rules. In Proceedings of NAACL. Paul Piwek and Svetlana Stoyanchev. 2011. Dataoriented monologue-to-dialogue generation. In Proceedings of ACL, pages 242–247. Paul Piwek, Hugo Hernault, Helmut Prendinger, and Mitsuru Ishizuka. 2007. T2d: Generating dialogues between virtual agents automatically from text. In Proceedings of Intelligent Virtual Agents. Verena Rieser and Oliver Lemon. 2008. Learning effective multimodal dialogue strategies from wizardof-oz data: Bootstrapping and evaluation. In Pro- ceedings of ACL. A. Rizzo, Kenji Sagae, E. Forbell, J. Kim, B. Lange, J. Buckwalter, J. Williams, T. Parsons, P. Kenny, David R. Traum, J. Difede, and B. Rothbaum. 2011. Simcoach: An intelligent virtual human system for providing healthcare information and support. In Proceedings of ITSEC. Jost Schatzmann, Karl Weilhammer, Matt Stuttle, and Steve Young. 2006. A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies. Knowledge Engineering Review, 21(2). Konrad Scheffler and Steve Young. 2002. Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning. In Proceedings of Human Language Technology Research. Natalie B. Steinhauser, Gwendolyn E. Campbell, Leanne S. Taylor, Simon Caine, Charlie Scott, Myroslava Dzikovska, and Johanna D. Moore. 2011. 1678 Talk like an electrician: Student dialogue mimick- ing behavior in an intelligent tutoring system. In Proceedings of AIED. David R. Traum, Priti Aggarwal, Ron Artstein, Susan Foutz, Jillian Gerten, Athanasios Katsamanis, Anton Leuski, Dan Noren, and William R. Swartout. 2012. Ada and grace: Direct interaction with museum visitors. In Proceedings of Intelligent Virtual Agents. G ¨okhan T u¨r, Dilek Z. Hakkani-T u¨r, Asli C ¸elikyilmaz. 2011. Towards ken language understanding: Dustin Hillard, and unsupervised spo- Exploiting query click logs for slot filling. In Proceedings of Interspeech. Adam Vogel and Dan Jurafsky. 2010. Learning to follow navigational directions. In Proceedings of ACL. Steve Young. 2010. Cognitive user interfaces. In IEEE Signal Processing Magazine. 1679