Advertisement

Annales Des Télécommunications

, Volume 44, Issue 1–2, pp 53–76 | Cite as

Le dialogue homme- machine en langue naturelle : un défi ?

  • Jacques Siroux
  • Michel Gilloux
  • Marc Guyomard
  • Christel Sorin
Article
  • 44 Downloads

Résumé

La mise en œuvre d’un dialogue homme-machine dans un système d’interrogation de base de données ou de base de connaissances est un problème difficile. Les auteurs présentent ici trois approches de ce problème : la modélisation du dialogue, illustrée par un travail linguistique et par des réalisations informatiques ; les principes de coopération dans le dialogue et leurs algorithmes associés ; et, enfin, l’approche intelligence artificielle fondée sur les actes de langage et la génération de plans. Pour terminer, ils abordent l’état actuel des possibilités d’utilisation des technologies vocales dans le cadre du dialogue homme-machine et les problèmes restant àrésoudre.

Mots clés

Dialogue homme machine Langage naturel Interrogation base donnée Modélisation Coopération Intelligence artificielle Synthèse parole Reconnaissance parole 

Man-machine dialogue in natural language : A Challenge?

Abstract

The implementation of a natural language manmachine dialogue in a data base or knowledge base query system is a difficult task. We present hereafter three different approaches to this problem : dialog modeling, exemplified through a linguistic scheme and several computational implementations ; the cooperation principles in a dialog and their associated algorithms ; and, lastly, the artificial intelligence approach based on speech acts theory and the techniques for generating and recognizing plans. We conclude by assessing the possible use of current speech processing techniques and by listing still unsolved problems.

Key words

Man machine dialogue Natural language Data base query Modelization Cooperation Artificial intelligence Speech synthesis Speech recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Bibliographie

  1. [1]
    Sperandio (J.-C), Lestang-Figeac (G). Simulation expérimentale de la synthèse vocale en dialogue oraux de communication homme-machine. Etude ergonomique.Rapport final d’étude au GRECO no 39 Communication parlée.IRAP, Paris, France (1986).Google Scholar
  2. [2]
    Sebillotte (S.), Bisseret (A.). La conception de scénarios interactifs.Rapport RR537, INRIA, France (1986).Google Scholar
  3. [3]
    Falzon (P.). Langages opératifs et compréhension operative. Thèse,Universitéde Paris 5, France (1986).Google Scholar
  4. [4]
    Ochsman (R. B.), Chapanis (A.). The effects of 10 communication modes on the behaviour of teams during cooperative problem solving.International Journal of Man-Machine Studies, USA (1974),6, pp. 579–619.CrossRefGoogle Scholar
  5. [5]
    Hayes (P.), Reddy (R.). Graceful interaction in man-machine communication.Proceedings of IJCAI, Jap. (1979),79.Google Scholar
  6. [6]
    Moran (T. P.). The command language grammar: a representation for the user interface of interactive computers systems.International Journal of Man-Machine Studies, USA (1981),15, pp. 3–50.CrossRefGoogle Scholar
  7. [7]
    hufit. Projet Esprit 385. Fraunhofe Institut/IAO, Stuttgart, RFA.Google Scholar
  8. [8]
    Morel (M.-A.). Vers une rhétorique de la conversation.DRLAV, Fr. (1983),29, pp. 29–68.Google Scholar
  9. [9]
    Moeschler (J.). Argumentation et conversation. Eléments critiques pour une analyse pragmatique du discours.Crédif-Hatier, Paris, Fr. (1985).Google Scholar
  10. [10]
    Morel (M.-A.). Analyse linguistique d’un corpus d’oral finalisé (Centre de renseignements sncf àParis).Rapport de fin de contrat au GRECO no 39 Communication parlée, CNRS, Fr. (1985).Google Scholar
  11. [11]
    Luzzati (D.). DIALORS : un système de dialogue oral simulé pour une tâche restreinte.Actes des 16ejournées d’études sur la parole, sfa, Hammamet, Tunisie (1987), pp. 183–186.Google Scholar
  12. [12]
    Rigaut (R.). Modélisation de certains phénomènes spontanés de l’oral. Rapport nt/laa/345, cnet, Fr. (1987).Google Scholar
  13. [13]
    Mc Keown (K.). Generating natural language text in response to questions about database structure. Ph. D. Thesis,University of Pensylvania, USA (1982).Google Scholar
  14. [14]
    Danlos (L.). Génération automatique de textes en langues naturelles.Masson, Paris (1985).Google Scholar
  15. [15]
    Austin (J. L.). How to do things with words.Oxford University Press, U.K. (1962).Google Scholar
  16. [16]
    Searle (J. R.). Speech acts: an essay in the philosophy of language.Cambridge University Press, USA (1969).Google Scholar
  17. [17]
    Searle (J. R.), Vanderveken (D.). Foundations of illocutionary logic.Cambridge University Press, USA (1985).MATHGoogle Scholar
  18. [18]
    Kaplan (S. J.). Cooperative response from a portable natural language query system.Artificial Intelligence, USA (1982),19, pp. 165–187.CrossRefGoogle Scholar
  19. [19]
    Gal (A.), Minker (J.). Des réponses coopératives données par une interface sgbd en langage naturel.Actes du 5eCongrès AFCET Reconnaissance des Formes et Intelligence Artificielle, Fr. (1985).Google Scholar
  20. [20]
    Sabah (G.). Un système de questions-réponses sur les rubriques professionnelles de l’annuaire téléphonique.Rapport no 31, CNRS, GR22,Groupe de Recherche C. F. Picard, Paris (1983).Google Scholar
  21. [21]
    Cuppens (F.), Demolombe (R.). Cooperative answering : a methodology to provide intelligent access to database.Rapport ONERA/CERT, Fr. (1987).Google Scholar
  22. [22]
    Cohen (P. R.), Perrault (R. C). Elements of a plan-based theory of speech acts.Cognitive Science, USA (1979),3, pp. 177–212.CrossRefGoogle Scholar
  23. [23]
    Perrault (R. C), Allen (J. F.). A plan-based analysis of indirect speech acts.American Journal of Computational Linguistics, USA (1980),6-3, pp. 167–182.Google Scholar
  24. [24]
    Allen (J. F.), Perrault (R. C). Analyzing intention in utterances.Artificial Intelligence, USA (1980),15, pp. 143–178.CrossRefGoogle Scholar
  25. [25]
    Sadek (M. D.), Guyomard (M.), Siroux (J.). Vers un système de dialogue basé sur les logiques intensionnelles et la planification des actes de langage.Actes du 6eCongrès AFCET Reconnaissance des Formes et Intelligence Artificielle, Fr. (1987), pp. 913-923.Google Scholar
  26. [26]
    Bunt (H. C), Beun (R. J.), Dols (F. H. H.), van der Linden (J. A.) and thoe Schwartzenberg (G. O.). The tendum dialogue system and its theoretical basis.IPO Annual Progress Report 19, Pays-Bas (1984).Google Scholar
  27. [27]
    Allen (J. F.). argot : a system review.Rapport TR 101,University of Rochester, USA (1982).Google Scholar
  28. [28]
    Grosz (B. J.). team : a transportable natural-language interface system.Proceedings Applied Natural Language Conference, Santa Monica, USA (1983).Google Scholar
  29. [29]
    Hoeppner (W.), Morik (K.), Marburger (H.). Talking it over: the natural language dialog system ham-ans. InCooperative Interfaces to Information Systems, Bolc (L.) et Jarke (M.) (éditeurs).Springer-Verlag, RFA (1986),Google Scholar
  30. [30]
    Jullien (C), Solvay (J.-P.). Person-machine dialogue for expert systems : the advice-giving case.Actes des journées internationales sur les systèmes experts, Avignon, Fr. (1987).Google Scholar
  31. [31]
    Wachtel (T.). Discourse structure.Loki Report NLI-1.1. Projet Esprit 107. Université de Hambourg, RFA (1985).Google Scholar
  32. [32]
    Woods (W. A.)et al. Speech understanding systems : final technical progress report.Report No. 3438, Bolt,Beranek and Newman Inc., Pittsburg, USA (1976).Google Scholar
  33. [33]
    Lesser (V. R.)et at. Organisation of the hearsay II speech understanding system.IEEE Trans. ASSP, USA (1975),23, no 1, pp. 11–23.Google Scholar
  34. [34]
    Levinson (S. E.), Rabiner (L. R.). A task-oriented mode speech understanding system.Bibliotheca phonetica, Bâle, Suisse (1985), no 12, pp. 149–196.Google Scholar
  35. [35]
    Morin (P.), Pierrel (J.-M.). partner : un système de dialogue oral homme-machine.Actes du congrès Cognitiva87, Paris, Fr. (1987).Google Scholar
  36. [36]
    Beroule (D.), Neel (F.). Une approche des problèmes liés à la communication parlée homme-machine.Actes du 4e Congrès AFCET Reconnaissance des formes et intelligence artificielle, Fr. (1984), pp. 53–63.Google Scholar
  37. [37]
    Siroux (J.), Gillet (D.). A system for man-machine communication using speech.Speech communication, Pays-Bas (1985),4, no 4, pp. 289–315.CrossRefGoogle Scholar
  38. [38]
    BIGORGNE (D.), COZANNET (A.), GUYOMARD (M.), MERCIER (G.), MICLET (L.), QUERRE (M.), SlROUX (J.). A versatile speaker dependent continuous speech understanding system.Proceedings of ICASSP, USA (1988),88, pp. 303–306.Google Scholar
  39. [39]
    Pierrel (J.-M.). Dialogue oral homme-machine.Hermès, Paris (1987).Google Scholar
  40. [40]
    ***greco no 39 cnrs. Dialogue oral homme-machine en situation orientée par l’action.Actes du 5e Congrès AFCET Reconnaissance des formes et intelligence artificielle, Fr. (1985), pp. 281-295.Google Scholar
  41. [41]
    Amalberti (R.), Carbonnell (N.), Falzon (P.). Stratégies de contrôle en situation d’interrogation téléphonique.Actes du séminaire «dialogue homme-machine àcomposante orale», greco no 39 Communication parlée, Fr. (1984), pp. 384–402.Google Scholar
  42. [42]
    Amalberti (R.), Carbonnell (N.), Falzon (P.). Communication orale homme-homme et communication orale homme-machine : un même modèle ?Actes du 3ecolloque international de l’association pour la recherche cognitive, Fr. (1988), pp. 231–246.Google Scholar
  43. [43]
    Van Katwijk (A. F. V.), Van Ness(F. L.), Bunt (H. G), Müller (H. F.), Leopold (F. F.). Naive subjects interacting with a conversing information system.IPO annual progress report 14, Pays-Bas (1979), pp. 105–112.Google Scholar
  44. [44]
    Van Katwijk (A. F. V.). Explorations in the experimental study of information dialogues.IPO annual progress report 16, Pays-Bas (1981), pp. 108–113.Google Scholar
  45. [45]
    Guyomard (M.), Siroux (J.). Constitution incrémentale d’un corpus ds dialogues oraux coopératifs.Actes des 16ejournées d’études sur la parole, sfa, Hammamet, Tunisie (5–9 oct. 1987), pp. 179–182.Google Scholar
  46. [46]
    Gazdar (G.). Pragmatics.Academic Press, U.K. (1979).Google Scholar
  47. [47]
    Grosz (B. J.). Discourse analysis. In Walker D .E. (ed.), Speech understanding research.Technical Report, Stanford Research Institute, Menlo Park, CA, USA (1976).Google Scholar
  48. [48]
    Popov (E.). Talking with computers in natural language.Springer-Verlag, Berlin, RFA (1986).MATHGoogle Scholar
  49. [49]
    Grau (B.). Analyse et représentation d’un texte d’après le thème du discours.Thèse de troisième cycle, Université de Paris VI, Fr. (1983).Google Scholar
  50. [50]
    Hendrix (G. G.). Expanding the utility of semantics networks through partitioning.Technical note 105, Stanford Research Institute, Menlo Park, CA, USA (1975).Google Scholar
  51. [51]
    Wahlster (W.), Marburger (H.), Jameson (A.), Buse-man (S.). Over-answering yes-no questions : extended responses in a nl interface to a vision system.Proceedings IJCAI, Karlsruhe, RFA (8-12 August 1983), pp. 643–646.Google Scholar
  52. [52]
    Allen (J. F.), Litman (D. J.). Plans, goals, and language.Proceedings of the IEEE, USA (juillet 1986), 74–7, pp. 939–947.Google Scholar
  53. [53]
    Janas (J. M.). On the feasibility of informative answers. Advances in data base theory, Gallaire (H.), Minker (J.), Nicolas (J. M.) éditeurs,Plenum Press, New York, USA (1981), 1, pp. 397–414.Google Scholar
  54. [54]
    Guyomard (M.), Siroux (J.). Suggestive and corrective answers: a single mechanism. « Structure of multimodal dialogues », Bouwhuis (D. G.), Taylor (M. M.), Néel (F). (éditeurs),North Holland, Pays-Bas (1988).Google Scholar
  55. [55]
    Reilly (R.). Ill-formedness and miscommunication in person-machine dialogue.Information and software Techno- logy (March 1987), 29, no 2, pp. 69–74.CrossRefGoogle Scholar
  56. [56]
    McCoy (K.). Cooperative responses to object related misconceptions : a thesis proposal.MS-CIS-83-89, Uni- versity of Pennsylvania, Philadelphia, USA (Nov. 1983).Google Scholar
  57. [57]
    Siklossy (L.). Question-asking question-answering sys- tems.International seminar on intelligent question-answering and data base systems, IRIA, Bonas (Gers), Fr. (21–30 juin 1977), pp. 151–163.Google Scholar
  58. [58]
    ViLNAT (A.). L’élaboration d’interventions pertinentes dans une conversation homme-machine.Thèse de 3e cycle, Université de Paris VI, (1984).Google Scholar
  59. [59]
    Webber (B.), Joshi (A.). Taking the initiative in natural language data base interactions : justifying why.Pro- ceedings 9th COLING, Prague, (1982) pp. 413–418.Google Scholar
  60. [60]
    Euzenat (B.), Normier (B.), Ogonowski (A.), Zani (G. P.). Saphir + Reseda, a new approach to intelligent data base access.Proceedings IJCAI, Los Angeles, USA (18-23 August 1985), pp. 855–857.Google Scholar
  61. [61]
    Joshi (A.), Webber (B.), Weischedel (R. M.). Preventing false inferences.Proceedings of Coling-84, Stanford Uni- versity, USA (2-6 July 1984), pp. 134–138.Google Scholar
  62. [62]
    Kayser (D.). Comment représenter la typicalité.Maté- riels et logiciels pour la 5e génération, afcet, Paris (5–7 mars 1985), pp. 177–163.Google Scholar
  63. [63]
    Perrault (C. R.). An application of default logic to speech act theory.Report No. CSLI-87-90, CSLI, USA (March 1987).Google Scholar
  64. [64]
    Mays (E.). Monitors as responses to questions : deter- mining competence.Proceedings national conference on artificial intelligence, USA (1982), pp. 421–423.Google Scholar
  65. [65]
    Armengaud (F.). La pragmatique.Que-sais-je, PUF, Paris (1985).Google Scholar
  66. [66]
    Appelt (D.E.). Planning natural-language utterances to satisfy multiple goals.Stanford Univ., Technical Report STAN-CS-82-918 (1982).Google Scholar
  67. [67]
    Fikes (R.), Nilsson (N. J.). strips : a new approach to the application of theorem proving to problem solving.Artificial intelligence, USA (1971), 2, pp. 189–208.Google Scholar
  68. [68]
    Moore (R. G). Reasoning about knowledge and action.Ph. D. Thesis, Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massa- chusetts Institute of Technology (1980).Google Scholar
  69. [69]
    Halpern (J. Y.), Moses (Y.). A guide to the modal logics of knowledge and belief : preliminary draft.Proceedings of IJCAI-85, USA (1985), pp. 480–490.Google Scholar
  70. [70]
    Levesque (H. J.). A logic of implicit and explicit belief.Proceedings of AAAI-84, USA (1984), pp. 198–202.Google Scholar
  71. [71]
    Fagin (R.), Halpern (J. Y.). Belief, awareness, and limited reasoning.Artificial intelligence, USA (1988),34, pp. 39–76.CrossRefMathSciNetGoogle Scholar
  72. [72]
    Haas (A. R.). A syntactic theory of belief and action.Artificial intelligence, USA (1986),28, pp. 245–292.MATHCrossRefMathSciNetGoogle Scholar
  73. [73]
    Perlis (D.). Languages with self-reference I: foundations.Artificial intelligence, USA (1985),25-3, pp. 301–322.CrossRefMathSciNetGoogle Scholar
  74. [74]
    Sacerdoti (E. D.). A structure for plans and behavior.Elsevier, New York, USA (1977).MATHGoogle Scholar
  75. [75]
    Schmidt (D. F.), Sridharan (N. S.), Goodson (J. L.). The plan recognition problem: an intersection of arti- ficial intelligence and psychology.Artificial intelligence, USA (1979), 10, pp. 45–83.Google Scholar
  76. [76]
    Cohen (P. R.), Levesque (H. J.). Speech acts and ratio- nality.Proceedings of the 23rd annual meeting of the ACL, USA (1985), pp. 49-60.Google Scholar
  77. [77]
    Wilensky (R.). Planning and understanding. A compu- tational approach to human reasoning.Addison-Wesley, USA (1983).Google Scholar
  78. [78]
    Klatt (D.). Review of text-to-speech conversion for english.Journal of the acoustical Society of America, USA (1987),82, 3, pp. 737–793.CrossRefGoogle Scholar
  79. [79]
    Stella (M.). Speech synthesis. In computer speech pro- cessing,Prentice Hall, Londres (1985), pp. 421–460.Google Scholar
  80. [80]
    Calliope. La parole et son traitement automatique.Masson, Paris, Fr. (1989).Google Scholar
  81. [81]
    Abbou (A.), Meyer (T.), Lefaucheur (I.). La commu- nication parlée. In : Les industries de la langue, Paris (1987), I, pp. 193–206 et II, pp. 43–86, daicadif.Google Scholar
  82. [82]
    Mariani (J.). Speech technology in Europe.Proceedings of European conference on speech technology, Edinburgh, U.K. (1987), pp. 431–439.Google Scholar
  83. [83]
    Baker (J. M.). State-of-the-art speech recognition : U.S. research and business update.Proceedings of European conference on speech technology, Edinburgh, U.K. (1987), pp. 440–447.Google Scholar
  84. [84]
    SoRIN (G), Larreur (D.), Llorca (R.). A rythm-based parser for text-to-speech systems in French.Proceedings of XIth ICPhS, Tallin, USSR (1987).Google Scholar
  85. [85]
    Rossi (M.). Peut-on prédire l’organisation prosodique du langage spontané ?Etudes de linguistique appliquées, Fr. (1987),66, pp. 20–48.Google Scholar
  86. [86]
    Danlos (L.), Emerard (F.), Laporte (E.). Synthesis of spoken messages from semantic representations.Proceedings of Coling, RFA (1986).Google Scholar
  87. [87]
    Houghton (G.), Pearson (M.). The production of spoken dialogue.First European Workshop on Language Generation, Royaumont, Fr. (1987).Google Scholar
  88. [88]
    Rossi (M.). L’intonation et l’organisation de l’énoncé.Phonetica, Karger, Suisse (1985),42, pp. 135–153.CrossRefGoogle Scholar
  89. [89]
    Ladd (D. R.). Even, focus and normal stress.Journal of Semantics, USA (1983),2, no 2, pp. 157–170.Google Scholar
  90. [90]
    Averbuch (A.),et al. Experiments with the Tangora 20 000 words speech recognizer.Proceedings of ICASSP-87, Dallas, USA (1987), pp. 701–704.Google Scholar
  91. [91]
    Baker (J. K.), Baker (J. M.). Large vocabulary natural language speech recognition in software.First European conference on speech technology, Edinburgh, U.K. (1987), p. 440.Google Scholar
  92. [92]
    Kurzweil (R.), Steingart (R.). The application of large vocabulary speech recognition and knowledge engineering to the creation of written documents.Proceedings of speech tech’88, New York, USA (1988), pp. 56-61.Google Scholar
  93. [93]
    Speech tech’88.Proceedings of the Voice Input/Output Applications Conference and Exhibition. Media Dimensions Inc., New York, USA (1988).Google Scholar
  94. [94]
    Kubala (F.)et al. Continuous speech recognition results on the Byblos system on the Darpa 1000-words resource management database.Proceedings of ICASSP-88, New York (1988), pp. 291–294.Google Scholar
  95. [95]
    Lee (K.), Hon (H.). Large-vocabulary speaker-independent continuous speech recognition using hmm.Proceedings of ICASSP-88, New York (1988), pp. 123-126.Google Scholar
  96. [96]
    Mergel (D.,) Paeseler (A.). Construction of language models for spoken databases queries.Proceedings of ICASSP-87, Dallas, USA (1987), pp. 844–847.Google Scholar
  97. [97]
    Young (S. J.), Rüssel (N. H.), Thornton (J. H. S.). Speech recognition in Vodis II.Proceedings of ICASSP-88, New York (1988), pp. 441–444.Google Scholar

Copyright information

© Springer-Verlag 1989

Authors and Affiliations

  • Jacques Siroux
    • 1
  • Michel Gilloux
    • 2
  • Marc Guyomard
    • 3
  • Christel Sorin
    • 4
  1. 1.IRISA-IUTLannion Cedex
  2. 2.CNET-LAA SLC/AIALannion Cedex
  3. 3.IRISA/ENSSATLannion Cedex
  4. 4.CNET-LAA TSS/RCPLannion Cedex

Personalised recommendations