Automatic generation of concise summaries of spoken dialogues in unrestricted domains

ABSTRACT

Automatic summarization of open domain spoken dialogues is a new research area. This paper introduces the task, the challenges involved, and presents an approach to obtain automatic extract summaries for multi-party dialogues of four different genres, without any restriction on domain. We address the following issues which are intrinsic to spoken dialogue summarization and typically can be ignored when summarizing written text such as newswire data: (i) detection and removal of speech disfluencies; (ii) detection and insertion of sentence boundaries; (iii) detection and linking of cross-speaker information units (question-answer pairs). A global system evaluation using a corpus of 23 relevance annotated dialogues containing 80 topical segments shows that for the two more informal genres, our summarization system using dialogue specific components significantly outperforms a baseline using TFIDF term weighting with maximum marginal relevance ranking (MMR).

REFERENCES

• 1: Eric Brill, Some advances in transformation-based part of speech tagging, Proceedings of the twelfth national conference on Artificial intelligence (vol. 1), p.722-727, October 1994, Seattle, Washington, United States
• 2: Jaime Carbonell , Jade Goldstein, The use of MMR, diversity-based reranking for reordering documents and producing summaries, Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, p.335-336, August 24-28, 1998, Melbourne, Australia [doi>10.1145/290941.291025]
• 3: J. S. Garofolo, E. M. Voorhees, C. G. P. Auzanne, and V. M. Stanford. Spoken document retrieval: 1998 evaluation and investigation of new metrics. In Proceedings of the ESCA workshop: Accessing information in spoken audio, pages 1-7. Cambridge, UK, Apr. 1999.
• 4: Marsal Gavaldà , Klaus Zechner , Gregory Aist, High performance segmentation of spontaneous speech using part of speech and trigger word information, Proceedings of the fifth conference on Applied natural language processing, p.12-15, March 31-April 03, 1997, Washington, DC [doi>10.3115/974557.974560]
• 5: Marti A. Hearst, TextTiling: segmenting text into multi-paragraph subtopic passages, Computational Linguistics, v.23 n.1, p.33-64, March 1997
• 6: Peter A. Heeman , James F. Allen, Intonational boundaries, speech repairs and discourse markers: modeling spoken dialog, Proceedings of the 35th annual meeting on Association for Computational Linguistics, p.254-261, July 07-12, 1997, Madrid, Spain
• 7: C. Hori and S. Furui. Improvements in automatic speech summarization and evaluation methods. In Proceedings of ICSLP-00, Beijing, China, October, pages 326-329, 2000.
• 8: D. Jurafsky, R. Bates, N. Coccaro, R. Martin, M. Meteer, K. Ries, E. Shriberg, A. Stolcke, P. Taylor, and C. V. Ess-Dykema. SwitchBoard discourse language modeling project, final report. Research Note 30, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 1998.
• 9: M. Kameyama, G. Kawai, and I. Arima. A real-time system for summarizing human-human spontaneous spoken dialogues. In Proceedings of the ICSLP-96, pages 681-684, 1996.
• 10: K. Koumpis and S. Renals. Transcription and summarization of voicemail speech. In Proceedings of ICSLP-00, Beijing, China, October, pages 688-91, 2000.
• 11: Julian Kupiec , Jan Pedersen , Francine Chen, A trainable document summarizer, Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval, p.68-73, July 09-13, 1995, Seattle, Washington, United States [doi>10.1145/215206.215333]
• 12: Linguistic Data Consortium. LDC. CallHome and CallFriend LVCSR databases, 1996.
• 13: Linguistic Data Consortium. LDC. Treebank-3: CD-ROM containing databases of dis uency annotated Switchboard transcripts (LDC99T42), 1999.
• 14: I. Mani, D. House, G. Klein, L. Hirschman, L. Obrst, T. Firmin, M. Chrzanowski, and B. Sundheim. The TIPSTER SUMMAC text summarization evaluation. Mitre Technical Report MTR 98W0000138, October 1998, 1998.
• 15: Mark T. Maybury , Inderjeet Mani, Advances in Automatic Text Summarization, MIT Press, Cambridge, MA, 1999
• 16: D. Marcu. Discourse trees are good indicators of importance in text. In Mani and Maybury {15}, pages 123-136.
• 17: M. Meteer, A. Taylor, R. MacIntyre, and R. Iyer. Dys uency annotation stylebook for the Switchboard corpus. Revised by Ann Taylor, June 1995, available on the LDC99T42 CD-ROM, published by LDC, 1995.
• 18: J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 19: G. J. Rath, A. Resnick, and T. R. Savage. The formation of abstracts by the selection of sentences. American Documentation, 12(2):139-143, 1961.
• 20: Norbert Reithinger , Michael Kipp , Ralf Engel , Jan Alexandersson, Summarizing multilingual spoken negotiation dialogues, Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, p.310-317, October 03-06, 2000, Hong Kong [doi>10.3115/1075218.1075258]
• 21: R. L. Rose. The communicative value of filled pauses in spontaneous speech. PhD thesis, University of Birmingham, Birmingham, UK, 1998.
• 22: E. E. Shriberg. Preliminaries to a Theory of Speech Dis uencies. PhD thesis, University ofBerkeley, Berkeley, CA, 1994.
• 23: Andreas Stolcke , Noah Coccaro , Rebecca Bates , Paul Taylor , Carol Van Ess-Dykema , Klaus Ries , Elizabeth Shriberg , Daniel Jurafsky , Rachel Martin , Marie Meteer, Dialogue act modeling for automatic tagging and recognition of conversational speech, Computational Linguistics, v.26 n.3, p.339-373, September 2000 [doi>10.1162/089120100561737]
• 24: A. Stolcke, E. Shriberg, R. Bates, M. Ostendorf, D. Hakkani, M. Plauche, G. T. ur, and Y. Lu. Automatic detection of sentence boundaries and dis uencies based on recognized words. In Proceedings of the ICSLP-98, Sydney, Australia, December, volume 5, pages 2247-2250, 1998.
• 25: S. Teufel and M. Moens. Sentence extraction as a classification task. In ACL/EACL-97 Workshop on Intelligent and Scalable Text Summarization, Madrid, Spain, 1997.
• 26: R. Valenza, T. Robinson, M. Hickey, and R. Tucker. Summarisation of spoken audio through information extraction. In Proceedings of the ESCA workshop: Accessing information in spoken audio, pages 111-116. Cambridge, UK, Apr. 1999.
• 27: Wolfgang Wahlster, Verbmobil - Translation of Face-To-Face Dialogs, Grundlagen und Anwendungen der Künstlichen Intelligenz, 17. Fachtagung für Künstliche Intelligenz, Humboldt-Universität zu, p.393-402, September 13-16, 1993
• 28: A. Waibel, M. Bett, and M. Finke. Meeting browser: Tracking and summarizing meetings. In Proceedings of the DARPA Broadcast News Workshop, 1998.
• 29: A. Waibel, M. Bett, F. Metze, K. Ries, T. Schaaf, T. Schultz, H. Soltau, H. Yu,and K. Zechner. Advances in automatic meeting record creation and access. In Proceedings of ICASSP-2001, Salt Lake City, UT, May, 2001.
• 30: Steve Whittaker , Julia Hirschberg , John Choi , Don Hindle , Fernando Pereira , Amit Singhal, SCAN: designing and evaluating user interfaces to support retrieval from speech archives, Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, p.26-33, August 15-19, 1999, Berkeley, California, United States [doi>10.1145/312624.312639]
• 31: K. Zechner. Automatic Summarization of Spoken Dialogues in Unrestricted Domains. PhD thesis, Language Technologies Institute, School of Computer Science, Carnegie Mellon University, forthcoming.
• 32: K. Zechner and A. Lavie. Increasing the coherence of spoken dialogue summaries by cross-speaker information linking. In Proceedings of the NAACL-01 Workshop on Automatic Summarization, Pittsburgh, PA, June, 2001.
• 33: Klaus Zechner , Alex Waibel, DiaSumm: flexible summarization of spontaneous dialogues in unrestricted domains, Proceedings of the 18th conference on Computational linguistics, July 31-August 04, 2000, Saarbrücken, Germany [doi>10.3115/992730.992786]
• 34: Klaus Zechner , Alex Waibel, Minimizing word error rate in textual summaries of spoken language, Proceedings of the first conference on North American chapter of the Association for Computational Linguistics, p.186-193, April 29-May 04, 2000, Seattle, Washington

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Linguistic processing

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models; Search process

General Terms:
Design, Experimentation, Languages, Performance