Book contents
- Frontmatter
- Contents
- List of contributors
- 1 Introduction
- Part I Joint construction
- 2 Communicative intentions and natural language generation
- 3 Pursuing and demonstrating understanding in dialogue
- 4 Dialogue and compound contributions
- Part II Reference
- Part III Handling uncertainty
- Part IV Engagement
- Part V Evaluation and shared tasks
- Author index
- Subject index
- References
2 - Communicative intentions and natural language generation
from Part I - Joint construction
Published online by Cambridge University Press: 05 July 2014
Book contents
- Frontmatter
- Contents
- List of contributors
- 1 Introduction
- Part I Joint construction
- 2 Communicative intentions and natural language generation
- 3 Pursuing and demonstrating understanding in dialogue
- 4 Dialogue and compound contributions
- Part II Reference
- Part III Handling uncertainty
- Part IV Engagement
- Part V Evaluation and shared tasks
- Author index
- Subject index
- References
Summary
Introduction
Natural language generation (NLG) has one significant disadvantage when compared with natural language understanding (NLU): the lack of a clear input format. NLU has as its starting point either a speech signal or text, both of which are well-understood representations. Input for NLG, on the other hand, is quite ill-defined and there is nothing close to consensus in the NLG community. This poses a fundamental challenge in doing research on NLG – there is no agreed-upon starting point.
The issue of input is particularly salient for NLG in interactive systems for one simple reason: interactive systems create their own communicative content. This is due to the role of these systems as dialogue partners, or conversational agents. The necessarily agentive nature of these systems requires them to decide why to speak and what to convey, as well as how to convey it.
Consider some other domains where NLG is used. In machine translation, for example, the system's job is to translate content from one human language to another. Here, the system does not have to create any content at all – that was already done by the human who created the source language text or speech. Work on automatic summarization is another example. Here the system's goal is to take pre-existing content and condense it.
Conversational agents, however, must create content. At a high level, this creation is driven by the need of the agent to communicate something. What the agent wants to accomplish by communicating is referred to as a communicative intention. If we can define communicative intentions, they can serve as a standard input representation to NLG for interactive systems.
- Type
- Chapter
- Information
- Natural Language Generation in Interactive Systems , pp. 13 - 33Publisher: Cambridge University PressPrint publication year: 2014
References
, , , , , , , , and (1998). Dialogue acts in VERBMOBIL-2 second edition. Technical Report Verbmobil Report 226, DFKI Saarbrücken, Universität Stuttgart, TU Berlin, Universität des Saarlandes.Google Scholar
(1983). Recognizing intentions from natural language utterances. In and , editors, Computational Models of Discourse, pages 107-166. MIT Press, Cambridge, MA.Google Scholar
, , , , , and (2001). Towards conversational human-computer interaction. AI Magazine, 22(4):27-37.Google Scholar
and (1997). Draft of DAMSL: Dialog act markup in several layers. Available from: http://www.cs.rochester.edu/research/cisd/resources/damsl/RevisedManual/. Accessed on 11/24/2013.Google Scholar
, , , , , , , , and (2006). Natural and intuitive multimodal dialogue for in-car applications: The Sammie system. In Proceedings of the European Conference on Artificial Intelligence, pages 612-616, Riva del Garda, Italy. Italian Association for Artificial Intelligence.Google Scholar
, , , , , , , , , , , , , and (2011). Spoken dialog challenge 2010: Comparison of live and control test results. In Proceedings ofthe SIGdial Conference on Discourse and Dialogue (SIGDIAL), pages 2-7, Portland, OR. Association for Computational Linguistics.Google Scholar
(2005). Towards Tractable Agent-based Dialogue. PhD thesis, Department of Computer Science, University of Rochester.Google Scholar
(2007). Towards flexible, domain-independent dialogue management using collaborative problem solving. In Proceedings of the Workshop on the Semantics and Pragmatics of Dialogue, pages 91-98, Rovereto, Italy. SemDial.Google Scholar
and (2005). A collaborative problem-solving model of dialogue. In Proceedings ofthe SIGdial Workshop on Discourse and Dialogue (SIGDIAL), pages 200-211, Lisbon, Portugal. Association for Computational Linguistics.Google Scholar
, , , , , and (1999). Survey of existing interactive systems. Available from http://www.ling.gu.se/projekt/trindi/publications.html. Accessed on 11/24/2013.Google Scholar
and (2003). RavenClaw: Dialog management using hierarchical task decomposition and an expectation agenda. In Proceedings ofthe European Conference on Speech Communication and Technology (EUROSPEECH), pages 597-600, Geneva, Switzerland. International Speech Communication Association.Google Scholar
, , , , , , , , , , , and (2010). Towards an ISO standard for dialogue act annotation. In Proceedings ofthe International Conference on Language Resources and Evaluation (LREC), Valletta, Malta. European Language Resources Association.Google Scholar
(2000). MIMIC: An adaptive mixed initiative spoken dialogue system for information queries. In Proceedings of the Conference on Applied Natural Language Processing, pages 97-104, Seattle, WA. Association for Computational Linguistics.Google Scholar
and (2000). Conflict resolution in collaborative planning dialogues. International Journal of Human-Computer Studies, 53(6):969-1015.CrossRefGoogle Scholar
and (1990). Rational interaction as the basis for communication. In , , and , editors, Intentions in Communication, pages 221-255. MIT Press, Cambridge, MA.Google Scholar
and (1979). Elements of aplan-based theory of speech acts. Cognitive Science, 3(3):177-212.CrossRefGoogle Scholar
, , and (1982). Beyond question answering. In and , editors, Strategies for Natural Language Processing, pages 245-274. Lawrence Erlbaum Associates, Hillsdale, NJ.Google Scholar
, , , and (1997). Reconstructed intentions in collaborative problem solving dialogues. In Working Notes of the AAAIFall Symposium on Communicative Action in Humans and Machines, Boston, MA. Association for the Advancement of Artificial Intelligence.Google Scholar
and (2010). Speak4it: Multimodal interaction for local search. In Proceedings ofthe International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction (ICMI-MLMI), article 10, Beijing, China. Association for Computing Machinery.Google Scholar
(1969). Utterer's meaning and intention. The Philosophical Review, 78(2):147-177.CrossRefGoogle Scholar
(1978). Focusing in dialog. In Proceedings ofthe Workshop on Theoretical Issues in Natural Language Processing, pages 96-103, Urbana, IL. Association for Computational Linguistics.Google Scholar
and (1996). Collaborative plans for complex group action. Artificial Intelligence, 86(2):269-357.CrossRefGoogle Scholar
and (1999). The evolution of SharedPlans. In and , editors, Foundations and Theories of Rational Agency, pages 227-262. Kluwer, Dordrecht, The Netherlands.Google Scholar
and (1986). Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3):175-204.Google Scholar
, , and (1996). Systematic design of spoken prompts. In Proceedings ofthe ACM SIGCHI Conference on Human Factors in Computing Systems (CHI), pages 157-164, Vancouver, Canada. Association for Computing Machinery.Google Scholar
and (1991). A tripartite plan-based model of dialogue. In Proceedings ofthe Annual Meeting ofthe Association for Computational Linguistics (ACL), pages 47-54, Berkeley, CA. Association for Computational Linguistics.Google Scholar
, , , , , and (2000). The LIMSI ARISE system. Speech Communication, 31(4):339-354.CrossRefGoogle Scholar
, , and (1990). On acting together. In Proceedings of the Conference on Artificial Intelligence (AAAI), pages 94-99, Boston, MA. AAAI Press.Google Scholar
and (1990). Discourse processing and commonsense plans. In , , and , editors, Intentions in Communication, pages 365-388. MIT Press, Cambridge, MA.Google Scholar
and (1988). Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243-281.CrossRefGoogle Scholar
(1991). A three-level model for plan exploration. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 39-46, Berkeley, CA. Association for Computational Linguistics.Google Scholar
, , , , , , , and (1999). Creating natural dialogs in the Carnegie Mellon Communicator system. In Proceedings ofthe European Conference on Speech Communication and Technology (EUROSPEECH), pages 1531-1534, Budapest, Hungary. International Speech Communication Association.Google Scholar
and De (1998). Dialogue systems. In , editor, Spoken Dialogues with Computers, pages 523-561. Academic Press, Orlando, FL.Google Scholar
(1975). Indirect speech acts. In and , editors, Speech Acts, pages 59-82. Academic Press, New York, NY.Google Scholar
and (2000). Dialogue management in the Mercury flight reservation system. In Proceedings of the ANLP/NAACL Workshop on Conversational Systems, pages 11-16, Seattle, WA. Association for Computational Linguistics.Google Scholar
(2002). A conversation acts model for generating spoken dialogue contributions. Computer Speech and Language, 16(3-4):313-352.CrossRefGoogle Scholar
and (1992). Conversation acts in task-oriented spoken dialogue. Computational Intelligence, 8(3):575-599.CrossRefGoogle Scholar
(1994). A Computational Theory of Grounding in Natural Language Conversation. PhD thesis, Department of Computer Science, University of Rochester.Google Scholar
(2000). 20 questions for dialogue act taxonomies. Journal of Semantics, 17(1):7-30.CrossRefGoogle Scholar
, , , , , , and (2000). JUPITER: A telephone-based conversational interface for weather information. IEEE Transactions on Speech and Audio Processing, 8(1):85-96.CrossRefGoogle Scholar