Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben
Erschienen in:
Conversational Interfaces Kapitel lesen Erstes Kapitel lesen

2012 | OriginalPaper | Buchkapitel

6. Statistical Approaches to Adaptive Natural Language Generation

verfasst von : Oliver Lemon, Srini Janarthanam, Verena Rieser

Erschienen in: Data-Driven Methods for Adaptive Spoken Dialogue Systems

Verlag: Springer New York

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Employing statistical models of users, generation contexts and of naturallanguages themselves has several potentially beneficial features: the ability to trainmodels on real data, the availability of precise mathematical methods foroptimisation, and the capacity to adapt robustly to previously unseensituations.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Vorheriges Kapitel Optimisation for POMDP-Based Spoken Dialogue Systems
Nächstes Kapitel Metrics and Evaluation of Spoken Dialogue Systems
Fußnoten
1
Similar to the internal user models applied in recent work on POMDP (partially observable markov decision process) dialogue managers [16, 18, 61] for estimation of user act probabilities.
 
2
Where a u, t is the predicted next user action at time t, IP s, t was the system’s information presentation action at t, and attributes s, t are the attributes selected by the system at t.
 
3
Note that the maximum possible number of sentences generated by the realiser is 18 for the full IP sequence summary+compare+recommend using all the attributes.
 
4
Note that the baseline does reasonably well in scenarios with variation introduced by only higher-level features (e.g. scenario 2. 2).
 
5
We will use italicised forms to represent the domain entities (e.g. broadband_filter) and double quotes to represent the referring expressions (e.g. “broadband filter”).
 
Literatur
1.
Akiba, T., Tanaka, H.: A Bayesian approach for User Modelling in Dialogue Systems. In: Proceedings of the 15th conference on Computational Linguistics - Volume 2, Kyoto (1994)
2.
Angeli, G., Liang, P., Klein, D.: A simple domain-independent probabilistic approach to generation. In: Proceedings of EMNLP (2010)
3.
Bell, A.: Language style as audience design. Lang. Soc. 13(2), 145–204 (1984)CrossRef
4.
Boidin, C., Rieser, V., Plas, L.V., Lemon, O., Chevelu, J.: Predicting how it sounds: Re-ranking alternative inputs to TTS using latent variables. In: Proc. of Interspeech/ICSLP, Special Session on Machine Learning for Adaptivity in Spoken Dialogue Systems (2009)
5.
Cawsey, A.: User Modelling in Interactive Explanations. User Modeling and User-Adapted Interaction 3(3), 221–247 (1993)CrossRef
6.
Chung, G.: Developing a flexible spoken dialog system using simulation. In: Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL) (2004)
7.
Clark, H.H., Murphy, G.L.: Audience design in meaning and reference. In: LeNy, J.F., Kintsch, W. (eds.), Language and comprehension. Amsterdam: North-Holland Publishing Company (1982)
8.
Clarkson, P.R., Rosenfeld, R.: Statistical Language Modeling Using the CMU-Cambridge Toolkit. In: Proc. of ESCA Eurospeech (1997)
9.
Cuayáhuitl, H., Renals, S., Lemon, O., Shimodaira, H.: Human-Computer Dialogue Simulation Using Hidden Markov Models. In: Proc. of the IEEE workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 290–295, San Juan, Puerto Rico, November (2005)
10.
Dale, R.: Cooking up referring expressions. In: Proc. ACL-1989 (1989)
11.
Demberg, V., Moore, J.: Information presentation in spoken dialogue systems. In: Proc. of the Conference of the European Chapter of the Association for Computational Linguistics (EACL) (2006)
12.
Dethlefs, N., Cuayáhuitl, H.: Hierarchical reinforcement learning and hidden markov models for task-oriented natural language generation. In: Proc. of 49th Annual Meeting of the Association for Computational Linguistics, 2011
13.
Dethlefs, N., Cuayáhuitl, H., Viethen, J.: Optimising natural language generation decision making for situated dialogue. In: Proc. of SIGdial Workshop on Discourse and Dialogue (2011)
14.
Dethlefs, N., Cuayahuitl, H.: Combining Hierarchical Reinforcement Learning and Bayesian Networks for Natural Language Generation in Situated Dialogue. In: ENLG (2011)
15.
Eckert, W., Levin,  E.,  Pieraccini, R.: User modeling for spoken dialogue system evaluation. In: Proc. of the IEEE workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 80–87. Santa Barbara, CA , USA, December 1997
16.
Gasic, M., Keizer, S., Mairesse, F., Schatzmann, J., Thomson, B., Young, S.: Training and Evaluation of the HIS POMDP Dialogue System in Noise. In: Proc. of SIGdial Workshop on Discourse and Dialogue, 2008
17.
Golland, D., Liang, P., Klein, D.: A game-theoretic approach to generating spatial descriptions,. In: Proceedings of EMNLP (2010)
18.
Henderson, J., Lemon, O.: Mixture Model POMDPs for Efficient Handling of Uncertainty in Dialogue Management. In: Proc. of the Annual Meeting of the Association for Computational Linguistics (2008)
19.
Isard, A., Oberlander, J., Matheson, C.: Speaking the users languages. IEEE Intell. Syst. Mag. 18, 40–45 (2003)CrossRef
20.
Issacs, E.A., Clark, H.H.: References in conversations between experts and novices. J. Exp. Psychol. Gen. 116, 26–37 (1987)CrossRef
21.
Janarthanam, S., Lemon, O.: Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems. In: Proc. ACL’10 (2010)
22.
Janarthanam, S., Lemon, O.: Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 69–78. Uppsala, Sweden, July 2010
23.
Janarthanam, S., Lemon, O.: A Wizard-of-Oz environment to study Referring Expression Generation in a Situated Spoken Dialogue Task. In: Proc. ENLG’09 (2009)
24.
Janarthanam, S., Lemon, O.: The GRUVE Challenge: Generating Routes under Uncertainty in Virtual Environments. In: Proceedings of ENLG / Generation Challenges (2011)
25.
Janarthanam, S., Lemon, O.: Adaptive referring expression generation in spoken dialogue systems: Evaluation with real users. In: Proceedings of SIGDIAL (2010)
26.
Janarthanam, S. Lemon, O.: A Two-tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies. In: Proc. SigDial’09 (2009)
27.
Janarthanam, S., Lemon, O.: A Two-tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies. In: Proc./ of the Annual SIGdial Meeting on Discourse and Dialogue (2009)
28.
Janarthanam, S., Hastie, H., Lemon, O., Liu, X.: ’The day after the day after tomorrow? ’ A machine learning approach to adaptive temporal expression generation: training and evaluation with real users. In: Proceedings of SIGDIAL, 2011
29.
Jung, S., Lee, C., Kim, K., Jeong, M., Lee, G.G.: Data-driven user simulation for automated evaluation of spoken dialog systems. Comput. Speech. Lang. 23, 479–509 (2009)CrossRef
30.
Koller, A., Petrick, R.: Experiences with planning for natural language generation. In: ICAPS (2008)
31.
Koller, A., Stone, M.: Sentence generation as planning. In: Proceedings of ACL (2007)
32.
Koller, A., Moore, J., di Eugenio, B., Lester, J., Stoia, L., Byron, D., Jon Oberlander, J., Striegnitz, K.: Shared task proposal: Instruction giving in virtual worlds. In: White, M., Dale, R. (eds.) Working group reports of the Workshop on Shared Tasks and Comparative Evaluation in Natural Language Generation (2007)
33.
Lemon, O.: Learning what to say and how to say it: joint optimization of spoken dialogue management and Natural Language Generation, Computer Speech and Language, 25(2), 210–221 (2011)CrossRef
34.
Lemon, O.: Adaptive natural language generation in dialogue using Reinforcement Learning. In:  Proc. of the 12th SEMdial Workshop on on the Semantics and Pragmatics of Dialogues, London, UK, June (2008)
35.
Lemon, O., Janarthanam, S., Rieser, V.: Generation under uncertainty. In: Proceedings of INLG / Generation Challenges (2010)
36.
Mairesse, F. Gasic, M., Jurcicek, F., Keizer, S. Thomson, B., Yu, K., Young, S.: Phrase-based statistical language generation using graphical models and active learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL) (2010)
37.
Moore Johanna, D., Foster, M.E., Lemon, O., White, M.: Generating tailored, comparative descriptions in spoken dialogue. In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Sociey Conference. AAAI Press (2004)
38.
Nakatsu, C.: Learning contrastive connectives in sentence realization ranking. In: Proc. of SIGdial Workshop on Discourse and Dialogue (2008)
39.
Paris, C.L.: Tailoring Object Descriptions to a User’s Level of Expertise. Comput. Ling. 14(3), 64–78 (1988)
40.
Polifroni, J., Walker, M.: Intensional Summaries as Cooperative Responses in Dialogue Automation and Evaluation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2008)
41.
Polifroni, J., Walker, M.: Learning database content for spoken dialogue system design. In: Proc. of the IEEE/ACL workshop on Spoken Language Technology (SLT) (2006)
42.
Reiter, E., Sripada, S., Hunter, J., Davy, I.: Choosing words in computer-generated weather forecasts. Artif. Intell. 167, 137–169 (2005)CrossRef
43.
Rieser, V., Lemon, O., Liu, X.: Optimising Information Presentation for Spoken Dialogue Systems. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1009–1018. Uppsala, Sweden, July 2010
44.
Rieser, V., Lemon, O.: Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems. In: Proc. of the Conference of European Chapter of the Association for Computational Linguistics (EACL), 2009
45.
Rieser, V., Keizer, S., Lemon, O., Liu, X.: Adaptive Information Presentation for Spoken Dialogue Systems: Evaluation with human subjects. In: Proceedings of ENLG (2011)
46.
Schlangen, D., Skantze, G.: A General, Abstract Model of Incremental Dialogue Processing. Dialog. Discourse 2(1), 710–718 (2011)
47.
Shapiro, D., Langley, P.: Separating skills from preference: Using learning to program by reward. In: Proc. ICML-02 (2002)
48.
Shapiro, D., Langley, P.: Separating skills from preference: Using learning to program by reward. In: Proc. of the 19th International Conference on Machine Learning (ICML), pp. 570–577, Sydney, Australia, July (2002)
49.
Skantze, G., Hjalmarsson, A.: Towards Incremental Speech Generation in Dialogue Systems. In: Proceedings of the 11th Annual SigDial Meeting on Discourse and Dialogue, Tokyo, Japan (2010)
50.
Stent, A., Prasad, R., Walker, M.: Trainable sentence planning for complex information presentation in spoken dialog systems. In: Association for Computational Linguistics (2004)
51.
Sutton, R., Barto, A.: Reinforcement Learning. MIT Press, Cambridge (1998)
52.
van Deemter, K.: Utility and Language Generation: The case of Vagueness. Journal of Philosophical Logic 607–632 (2009)
53.
van Deemter, K.: What game theory can do for NLG: the case of vague language. In:  12th European Workshop on Natural Language Generation (ENLG) (2009)
54.
Walker, M., Passonneau, R., Boland, J.: Quantitative and qualitative evaluation of DARPA Communicator spoken dialogue systems. In: Proc. of the Annual Meeting of the Association for Computational Linguistics (ACL) (2001)
55.
Walker, M., Stent, A., Mairesse, F., Prasad, R.: Individual and domain adaptation in sentence planning for dialogue. J. Artif. Intell. Res. (JAIR) 30, 413–456 (2007)
56.
Walker, M.A., Kamm, C.A., Litman, D.J.: Towards Developing General Models of Usability with PARADISE. Nat. Lang. Eng., 6(3), 363–377 (2000)CrossRef
57.
White, M., Rajkumar, R., Martin, S.: Towards broad coverage surface realization with ccg. In: In Proceedings of the Workshop on Using Corpora for NLG: Language Generation and Machine Translation (UCNLG + MT (2007)
58.
Whittaker, S., Walker, M., Moore, J., Whittaker, S., Walker, M., Moore, J.: Fish or fowl: A Wizard of Oz evaluation of dialogue strategies in the restaurant domain. In: Proc. of the International Conference on Language Resources and Evaluation (LREC) (2002)
59.
Winterboer, A., Hu, J., Moore, J.D., Nass, C.: The influence of user tailoring and cognitive load on user performance in spoken dialogue systems. In: Proc. of the 10th International Conference of Spoken Language Processing (Interspeech/ICSLP) (2007)
60.
61.
Young, S.J., Schatzmann, J., Weilhammer, K., Ye, H.: The Hidden Information State Approach to Dialog Management. In: ICASSP 2007 (2007)
62.
Young, S., Gašić, M., Keizer, S.,  Mairesse, F., Thomson, B., Yu, K.: The Hidden Information State model: a practical framework for POMDP based spoken dialogue management. Comput. Speech. Lang. 24(2), 150–174 (2009)CrossRef
Metadaten
Titel
Statistical Approaches to Adaptive Natural Language Generation
verfasst von
Oliver Lemon
Srini Janarthanam
Verena Rieser
Copyright-Jahr
2012
Verlag
Springer New York
Buch
Data-Driven Methods for Adaptive Spoken Dialogue Systems

Print ISBN: 978-1-4614-4802-0

Electronic ISBN: 978-1-4614-4803-7

Copyright-Jahr: 2012

DOI
https://doi.org/10.1007/978-1-4614-4803-7_6

Neuer Inhalt

    Bildnachweise