An unsupervised method for learning generation dictionaries for spoken dialogue systems by mining user reviews

ABSTRACT

Spoken language generation for dialogue systems requires a dictionary of mappings between the semantic representations of concepts that the system wants to express and the realizations of those concepts. Dictionary creation is a costly process; it is currently done by hand for each dialogue domain. We propose a novel unsupervised method for learning such mappings from user reviews in the target domain and test it in the restaurant and hotel domains. Experimental results show that the acquired mappings achieve high consistency between the semantic representation and the realization and that the naturalness of the realization is significantly higher than the baseline.

REFERENCES

• 1: Baptist, L. and Seneff, S. 2000. Genesis-ii: A versatile system for language generation in conversational system applications. In Proceedings of the International Conference on Spoken Language Processing (ICSLP). Vol. 3. 271--274.
• 2: Regina Barzilay , Mirella Lapata, Collective content selection for concept-to-text generation, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, p.331-338, October 06-08, 2005, Vancouver, British Columbia, Canada [doi>10.3115/1220575.1220617]
• 3: Regina Barzilay , Mirella Lapata, Aggregation via set partitioning for natural language generation, Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, p.359-366, June 04-09, 2006, New York, New York [doi>10.3115/1220835.1220881]
• 4: Regina Barzilay , Lillian Lee, Bootstrapping lexical choice via multiple-sequence alignment, Proceedings of the ACL-02 conference on Empirical methods in natural language processing, p.164-171, July 06, 2002 [doi>10.3115/1118693.1118715]
• 5: Regina Barzilay , Lillian Lee, Learning to paraphrase: an unsupervised approach using multiple-sequence alignment, Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, p.16-23, May 27-June 01, 2003, Edmonton, Canada [doi>10.3115/1073445.1073448]
• 6: Regina Barzilay , Kathleen R. McKeown, Extracting paraphrases from a parallel corpus, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.50-57, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073020]
• 7: Bobrow, D. G., Kaplan, R. M., Kay, M., Norman, D. A., Thompson, H., and Winograd, T. 1977. GUS, a frame driven dialog system. Artif. Intel. 8, 155--173.
• 8: Eric Brill, A simple rule-based part of speech tagger, Proceedings of the third conference on Applied natural language processing, March 31-April 03, 1992, Trento, Italy [doi>10.3115/974499.974526]
• 9: Chambers, N. and Allen, J. 2004. Stochastic language generation in a dialogue system: Toward a domain independent generator. In Proceedings of the 8th SIGDIAL Workshop on Discourse and Dialog. 9--18.
• 10: John Chen , Srinivas Bangalore , Owen Rambow , Marilyn A. Walker, Towards automatic generation of natural language generation systems, Proceedings of the 19th international conference on Computational linguistics, p.1-7, August 24-September 01, 2002, Taipei, Taiwan [doi>10.3115/1072228.1072366]
• 11: Oren Etzioni , Michael Cafarella , Doug Downey , Ana-Maria Popescu , Tal Shaked , Stephen Soderland , Daniel S. Weld , Alexander Yates, Unsupervised named-entity extraction from the web: an experimental study, Artificial Intelligence, v.165 n.1, p.91-134, June 2005 [doi>10.1016/j.artint.2005.03.001]
• 12: Fellbaum, C. 1998. WordNet: An Electronic Lexical Database (Language, Speech, and Communication). The MIT Press.
• 13: Feng, J., Reddy, S., and Saraçlar, M. 2005. Webtalk: Mining websites for interactively answering questions. In Proceedings of the 9th European Conference on Speech Communication and Technology. 2485--2488.
• 14: Daniel Gildea , Daniel Jurafsky, Automatic labeling of semantic roles, Computational Linguistics, v.28 n.3, p.245-288, September 2002 [doi>10.1162/089120102760275983]
• 15: Goddeau, D., Meng, H., Polifroni, J., Seneff, S., and Busayapongchai, S. 1996. A form-based dialogue manager for spoken language applications. In Proceedings of the International Conference on Spoken Language Processing (ICSLP). Vol. 2. 701--704.
• 16: Paul Heisterkamp, Linguatronic product-level speech system for Mercedes-Benz cars, Proceedings of the first international conference on Human language technology research, p.1-2, March 18-21, 2001, San Diego [doi>10.3115/1072133.1072199]
• 17: Higashinaka, R., Prasad, R., and Walker, M. 2005. Augmenting variation of system utterances using corpora in spoken dialogue systems. In Proceedings of 2005 IEEE Automatic Speech Recognition and Understanding Workshop. 262--267.
• 18: Ryuichiro Higashinaka , Rashmi Prasad , Marilyn A. Walker, Learning to generate naturalistic utterances using reviews in spoken dialogue systems, Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, p.265-272, July 17-18, 2006, Sydney, Australia [doi>10.3115/1220175.1220209]
• 19: Higashinaka, R., Sudoh, K., and Nakano, M. 2006. Incorporating discourse features into confidence scoring of intention recognition results in spoken dialogue systems. Speech Comm. 48, 3--4, 417--436.
• 20: Julia Hirschberg , Diane Litman, Now let's talk about now: identifying cue phrases intonationally, Proceedings of the 25th annual meeting on Association for Computational Linguistics, p.163-171, July 06-09, 1987, Stanford, California [doi>10.3115/981175.981198]
• 21: Minqing Hu , Bing Liu, Mining and summarizing customer reviews, Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, August 22-25, 2004, Seattle, WA, USA [doi>10.1145/1014052.1014073]
• 22: Nobuhiro Kaji , Masaru Kitsuregawa, Automatic construction of polarity-tagged corpus from HTML documents, Proceedings of the COLING/ACL on Main conference poster sessions, p.452-459, July 17-18, 2006, Sydney, Australia
• 23: Kim, S.-M., Pantel, P., Chklovski, T., and Pennacchiotti, M. 2006. Automatically assessing review helpfulness. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 423--430.
• 24: Knott, A. 1996. A Data-Driven Methodology for Motivating a Set of Coherence Relations. Ph.D. thesis, University of Edinburgh, Edinburgh.
• 25: Langkilde-Geary, I. 2002. An empirical verification of coverage and correctness for a general-purpose sentence generator. In Proceedings of the International Natural Language Generation Conference (INLG). 17--24.
• 26: Mirella Lapata , Frank Keller, Web-based models for natural language processing, ACM Transactions on Speech and Language Processing (TSLP), v.2 n.1, p.3-es, February 2005 [doi>10.1145/1075389.1075392]
• 27: Benoit Lavoie , Owen Rambow, A fast and portable realizer for text generation systems, Proceedings of the fifth conference on Applied natural language processing, p.265-268, March 31-April 03, 1997, Washington, DC [doi>10.3115/974557.974596]
• 28: Lin, D. 1998. Dependency-based evaluation of MINIPAR. In Proceedings of the Workshop on the Evaluation of Parsing Systems.
• 29: Dekang Lin , Patrick Pantel, Discovery of inference rules for question-answering, Natural Language Engineering, v.7 n.4, p.343-360, December 2001 [doi>10.1017/S1351324901002765]
• 30: Mairesse, F. and Walker, M. 2007. Personage: Personality generation for dialogue. In Proceedings of the 45th ACL.
• 31: Melčuk, I. A. 1988. Dependency Syntax: Theory and Practice. SUNY, Albany, NY.
• 32: Moore, J. D., Foster, M. E., Lemon, O., and White, M. 2004. Generating tailored, comparative descriptions in spoken dialogue. In Proceedings of the 17th International Florida Artificial Intelligence Research Society Conference.
• 33: Alice H. Oh , Alexander I. Rudnicky, Stochastic language generation for spoken dialogue systems, ANLP/NAACL 2000 Workshop on Conversational systems, p.27-32, May 04-04, 2000, Seattle, Washington [doi>10.3115/1117562.1117568]
• 34: Pantel, P. and Ravichandran, D. 2004. Automatically labeling semantic classes. In Proceedings of Human Language Technology Conference of the North American Chapter of the ACL (HLT/NAACL). 321--328.
• 35: Roberto Pieraccini , David Lubensky, Spoken language communication with machines: the long and winding road from research to business, Proceedings of the 18th international conference on Innovations in Applied Artificial Intelligence, p.6-15, June 22-24, 2005, Bari, Italy [doi>10.1007/11504894_2]
• 36: Ana-Maria Popescu , Oren Etzioni, Extracting product features and opinions from reviews, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, p.339-346, October 06-08, 2005, Vancouver, British Columbia, Canada [doi>10.3115/1220575.1220618]
• 37: Prasad, R., Joshi, A., Dinesh, N., Lee, A., Miltsakaki, E., and Webber, B. 2005. The Penn Discourse TreeBank as a resource for natural language generation. In Proceedings of the Corpus Linguistics Workshop on Using Corpora for Natural Language Generation.
• 38: Owen Rambow , Monica Rogati , Marilyn A. Walker, Evaluating a trainable sentence planner for a spoken dialogue system, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.434-441, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073068]
• 39: Ehud Reiter , Robert Dale, Building natural language generation systems, Cambridge University Press, New York, NY, 2000
• 40: Ehud Reiter , Somayajulu Sripada, Squibs and discussions: human variation and lexical choice, Computational Linguistics, v.28 n.4, p.545-553, December 2002 [doi>10.1162/089120102762671981]
• 41: Reiter, E., Sripada, S., and Robertson, R. 2003. Acquiring correct knowledge for natural language generation. J. Artif. Intel. Resear. 18, 491--516.
• 42: Seneff, S. and Polifroni, J. 2000. Formal and natural language generation in the mercury conversational system. In Proceedings of the International Conference on Spoken Language Processing. (ICSLP). Vol. 2. 767--770.
• 43: Snyder, B. and Barzilay, R. 2007. Database-text alignment via structured multilabel classification. In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI). 1713--1718.
• 44: Soderland, S. 2007. Moving from textual relations to ontologized relations. In Proceedings of the AAAI Spring Symposium on Machine Reading.
• 45: Amanda Stent , Rashmi Prasad , Marilyn Walker, Trainable sentence planning for complex information presentation in spoken dialog systems, Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p.79-es, July 21-26, 2004, Barcelona, Spain [doi>10.3115/1218955.1218966]
• 46: Theune, M. 2003. From monologue to dialogue: natural language generation in OVIS. In AAAI Spring Symposium on Natural Language Generation in Written and Spoken Dialogue. 141--150.
• 47: Peter D. Turney, Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, July 07-12, 2002, Philadelphia, Pennsylvania [doi>10.3115/1073083.1073153]
• 48: Walker, M., Rambow, O., and Rogati, M. 2002. Training a sentence planner for spoken dialogue using boosting. Comput. Speech Lang. 16, 3-4.
• 49: White, M. and Caldwell, T. 1998. EXEMPLARS: A practical, extensible framework for dynamic text generation. In Proceedings of the International Natural Language Generation Conference (INLG). 266--275.
• 50: Wilson, T., Wiebe, J., and Hwa, R. 2004. Just how mad are you? finding strong and weak opinion clauses. In Proceedings of AAAI. 761--769.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Language generation

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Natural language

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Natural language interfaces

General Terms:
Human Factors, Languages

Keywords:
Natural language generation, generation dictionary, spoken dialogue systems, user reviews