Elamur Research⌕
☰
home / papers / 1997 / Discourse Segmentation by Human and Automated Means

Discourse Segmentation by Human and Automated Means

Paper · 1997 · Rebecca J. Passonneau and Diane J. Litman

Summary

Discourse research widely assumes that multi-utterance units (discourse segments) interact with linguistic form, yet there is little agreement on what such segments are or how to identify them. Passonneau and Litman address this in two stages, using a corpus of spontaneous spoken narrative monologues (Chafe 1980). First, untrained subjects segmented the narratives, using an everyday notion of what the speaker was trying to do. Their boundary placements agreed far beyond chance, which supports intention-based segments as an empirically valid unit. Second, boundaries derived from these human judgments served as a gold standard for automatic segmenters. An initial set of algorithms each relied on a single cue type: referential noun phrases, cue words, or pauses. The authors then built improved algorithms through manual error analysis and through machine learning over large feature sets. Evaluated on held-out narratives, algorithms that combine several knowledge sources outperformed single-cue ones and came close to human performance. The study offers an early, quantitative methodology for validating discourse annotation and for linking it to computable utterance features.

Key points

  • Data: spontaneous narrative monologues from Chafe's (1980) spoken narrative corpus. The illustrative excerpt has boys helping a fallen cyclist gather pears.
  • Human segmentation: naive subjects, not trained coders, marked boundaries using speaker intention as the criterion. Agreement on boundaries was highly statistically significant.
  • First algorithm set: each algorithm used one cue type (referential NPs, cue words such as "well anyway", or pauses). Each was scored by how well it matched the subject-derived boundaries.
  • Second algorithm set: built using error analysis plus machine learning. The references cite C4.5 (Quinlan 1993). Combining features from multiple sources improved results on a new test set.
  • Context from related work: reported reliability elsewhere includes:
    • percent agreement of 74.3–95.1% in Grosz and Hirschberg (1992);
    • kappa ≥ .8 with speech versus .56–.63 from text alone in Hirschberg and Nakatani (1996);
    • average pairwise kappa of .45 in Flammia and Zue (1995).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Columbia UniversityNew York · United States149 works · 48,852 citations🏢AT&TBedminster · United States29 works · 15,393 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Discourse analysis · 394 works

Cite

Cite as Rebecca J. Passonneau and Diane J. Litman. 1997. Discourse Segmentation by Human and Automated Means. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

@article{passonneau1997discourse,
  title = {{Discourse Segmentation by Human and Automated Means}},
  author = {Rebecca J. Passonneau and Diane J. Litman},
  journal = {Computational Linguistics},
  year = {1997},
  doi = {10.5555/972684.972689},
  url = {https://doi.org/10.5555/972684.972689}
}

References

76 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abney, Steven P. 1990. Rapid incremental parsing with repair. In Proceedings of the 6th New OED Conference: Electronic Text Research, pages 1-9. find
  2. Anderson, Anne H., M. Bader, E. G. Bard, E. Boyle, G. Doherty, S. Garrod, S. Isard, J. Kowtko, J. McAllister, J. Miller, C. Sotillo, H. S. Thompson, and R. Weinert. 1991. The HCRC Map Task corpus. Language and Speech, 34:351-366. find
  3. Aone, Chinatsu and Scott W. Bennett. 1995. Evaluating automated and manual acquisition of anaphora resolution strategies. In Proceedings of the 33rd Annual Meeting, pages 122-129. Association for Computational Linguistics.
  4. Brieman, Leo, J. Friedman, R. Olshen, and C. Stone. 1984. Classij~'cation and Regression Trees. Wadsworth and Brooks. find
  5. Butterworth, Brian. 1980. Evidence from pauses in speech. In Brian Butterworth, editor, Language Production. Academic Press, London, pages 155-176. find
  6. Carberry, Sandra. 1990. Plan Recognition in Natural Language Dialogue. MIT Press, Cambridge, MA. find
  7. Carletta, Jean. 1996. Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22(2):249-254.
  8. Chafe, Wallace L. 1980. The Pear Stories: Cognitive, Cultural and Linguistic Aspects of Narrative Production. Ablex Publishing Corporation, Norwood, NJ. find
  9. Cochran, William G. 1950. The comparison of percentages in matched samples. Biometrika, 37:256-266. find
  10. Cohen, Robin. 1984. A computational theory of the function of clue words in argument understanding. In Proceedings of COLING84, pages 251-258, Stanford. find
  11. Dale, Robert. 1992. Generating Referring Expressions. MIT Press, Cambridge, MA. find
  12. Duncan, Starkey D. and Donald W. Fiske. 1977. Face-to-face Interaction. Lawrence Erlbaum Associates, Hillside, NJ. find
  13. Flammia, Giovanni and Victor Zue. 1995. Empirical evaluation of human performance and agreement in parsing discourse constituents in spoken dialogue. In Eurospeech 1995. find
  14. Gale, William, Ken W. Church, and David Yarowsky. 1992. Estimating upper and lower bounds on the performance of word-sense disambiguation programs. In Proceedings of the 30th Annual Meeting, pages 249-256, Newark, DE. Association for Computational Linguistics. find
  15. Grosz, Barbara J. 1977. The Representation and Use of Focus in Dialogue Understanding. find
  16. Ph.D. thesis, University of California, Berkeley. find
  17. Grosz, Barbara and Julia Hirschberg. 1992. Some intonational characteristics of discourse structure. In Proceedings of the International Conference on Spoken Language Processing (ICSLP). find
  18. Grosz, Barbara J., Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203-226.
  19. Grosz, Barbara J. and Candace L. Sidner. 1986. Attention, intentions and the structure of discourse. Computational Linguistics, 12:175-204.
  20. Hearst, Marti A. 1993. TextTiling: A quantitative approach to discourse segmentation. Technical Report 93/24, Sequoia 2000 Technical Report, University of California, Berkeley. find
  21. Hearst, Marti A. 1994. Multi-paragraph segmentation of expository text. In Proceedings of the 32nd Annual Meeting, pages 9-16. Association for Computational Linguistics. find
  22. Hindle, Donald. 1983. Deterministic parsing of syntactic non-fluencies. In Proceedings of the 21st Annual Meeting, pages 123-128. Association for Computational Linguistics. find
  23. Hirschberg, Julia. 1990. Accent and discourse context: Assigning pitch accent in synthetic speech. In Proceedings of the Eighth National Conference on Artificial Intelligence (AAAD, pages 952-957. find
  24. Hirschberg, Julia. 1991. Using text analysis to predict intonational boundaries. In Proceedings of the Second European Conference on Speech Communication and Technology. find
  25. Hirschberg, Julia and Diane Litman. 1993. Empirical studies on the disambiguation of cue phrases. Computational Linguistics, 19(3):501-530.
  26. Hirschberg, Julia and Christine H. Nakatani. 1996. A prosodic analysis of discourse segments in direction-giving monologues. find
  27. In Proceedings of the 34th Annual Meeting, pages 286-293. Association for Computational Linguistics. find
  28. Hirschberg, Julia and Janet Pierrehumbert. 1986. The intonational structuring of discourse. In Proceedings of the 24th Annual Meeting, pages 136-144. Association for Computational Linguistics. find
  29. Hobbs, Jerry R. 1979. Coherence and coreference. Cognitive Science, 3(1):67-90. find
  30. Hwang, Chung H. and Lehnart K. Schubert. 1992. Tense trees as the 'fine structure' of discourse. In Proceedings of the 30th Annual Meeting, pages 232-240. Association for Computational Linguistics. find
  31. Isard, Amy and Jean Carletta. 1995. Replicability of transaction and action coding in the Map Task Corpus. In AAAI 1995 Spring Symposium Series: Empirical Methods in Discourse Interpretation and Generation, pages 60-66. find
  32. Kozima, Hideki. 1993. Text segmentation based on similarity between words. In Proceedings of the 31st Annual Meeting (Student Session), pages 286-288. find
  33. Krippendorff, Klaus. 1980. Content Analysis. Sage Publications, Beverly Hills, CA. find
  34. Levy, Elena. 1984. Communicating Thematic Structure in Narrative Discourse: The Use of Referring Terms and Gestures. Ph.D. thesis, University of Chicago. find
  35. Lewis, David D. and Jason Catlett. 1994. Heterogeneous uncertainty sampling for supervised learning. In W. W. Cohen and H. Hirsh, editors, Proceedings of the Eleventh International Conference on Machine Learning (ML-94), pages 148-156. Morgan Kaufmann. find
  36. Linde, Charlotte. 1979. Focus of attention and the choice of pronouns in discourse. In T. Giv6n, editor, Syntax and Semantics: Discourse and Syntax. Academic Press, New York, pages 337-354. find
  37. Litman, Diane J. 1994. Classifying cue phrases in text and speech using machine learning. In Proceedings of the 12th National Conference on Artificial Intelligence (AAAI), pages 806-813. find
  38. Litman, Diane J. 1996. Cue phrase classification using machine learning. find
  39. Journal of Arti~'cial Intelligence Research, 5:53-94. find
  40. Litman, Diane J. and James Allen. 1990. Discourse processing and commonsense plans. In P. R. Cohen, J. Morgan, and M. E. Pollack, editors, Intentions in Communication. MIT Press, Cambridge, MA. find
  41. Litman, Diane J. and Rebecca J. Passonneau. 1995a. Combining multiple knowledge sources for discourse segmentation. In Proceedings of the 33rd Annual Meeting, pages 108-115. Association for Computational Linguistics. find
  42. Litman, Diane J. and Rebecca J. Passonneau. 1995b. Developing algorithms for discourse segmentation. In AAAI 1995 find
  43. Spring Symposium Series: Empirical Methods in Discourse Interpretation and Generation, pages 85-91. Mann, William C. and Sandra Thompson. 1988. Rhetorical structure theory: towards a functional theory of text organization. TEXT, 8:243-281. find
  44. Marslen-Wilson, William, Elena Levy, and Lorraine K. Tyler. 1982. Producing interpretable discourse: The establishment and maintenance of reference. In R. J. Jarvella and W. Klein, editors, Speech, Place and Action. John Wiley and Sons Ltd., New York, pages 339-378. find
  45. Mokros, Hartmut B. 1984. Patterns of Persistence and Change in the Sequencing of Nonverbal Actions. Ph.D. thesis, University of Chicago. find
  46. Moore, Johanna D. and Cecile Paris. 1993. Planning text for advisory dialogues: Capturing intentional and rhetorical information. Computational Linguistics, 19:652-694. find
  47. Moore, Johanna D. and Martha E. Pollack. 1992. A problem for RST: The need for multMevel discourse analysis. Computational Linguistics, 18(4):537-544. find
  48. Morris, Jane and Graeme Hirst. 1991. Lexical cohesion computed by thesaural relations as an indicator of the structure of text. Computational Linguistics, 17:21-48.
  49. Moser, Megan and Johanna Moore. 1995. Investigating cue selection and placement in tutorial discourse. In Proceedings of the 33rd Annual Meeting, pages 130-135. Association for Computational Linguistics. find
  50. Moser, Megan, Johanna D. Moore, and Erin Glendening. 1995. Instructions for coding Sherlock explanations: Identifying segments, relations and minimal units. Technical Report 96-17, University of Pittsburgh, Department of Computer Science. find
  51. Nakatani, Christine H., Julia Hirschberg, and Barbara J. Grosz. 1995. Discourse structure in spoken language: Studies on speech corpora. In AAAI 1995 Spring Symposium Series: Empirical Methods in Discourse Interpretation and Generation, pages 106-112. find
  52. Passonneau, Rebecca J. 1993. Getting and keeping the center of attention. In R. Weischedel and M. Bates, editors, Challenges in Natural Language Processing. find
  53. Passonneau, Rebecca J. 1994. Protocol for coding discourse referential noun phrases and their antecedents. Technical report, Columbia University. find
  54. Passonneau, Rebecca J. 1996. Using centering to relax Gricean informational constraints on discourse anaphoric noun phrases. Language and Speech, 39:229-264. find
  55. Passonneau, Rebecca J. and Diane J. Litman. 1993. Intention-based segmentation: Human reliability and correlation with linguistic cues. In Proceedings of the 31st Annual Meeting, pages 148-155. Association for Computational Linguistics. find
  56. Passonneau, Rebecca J. and Diane J. Litman. 1996. Empirical analysis of three dimensions of spoken discourse: Segmentation, coherence and linguistic devices. In E. Hovy and D. Scott, editors, Computational and Conversational Discourse. find
  57. Pierrehumbert, Janet and Julia Hirschberg. 1987. The meaning of intonational contours in the interpretation of discourse. Technical Report TM 11225-870325-07, AT&T Bell Laboratories. find
  58. Pitrelli, J., Mary Beckman, and Julia Hirschberg. 1994. Evaluation of prosodic transcription labeling reliability in the ToBI framework. In Proceedings oflCSLP. find
  59. Polanyi, Livya. 1988. A formal model of discourse structure. Journal of Pragmatics, 12:601-638. find
  60. Quinlan, John Ross. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann.
  61. Reichman, Rachel. 1985. Getting Computers to Talk Like You and Me. MIT Press, Cambridge, MA. find
  62. Reynar, Jeffrey C. 1994. An 'automatic method of finding topic boundaries. In Proceedings of the 32nd Annual Meeting (Student Session), pages 331-333. find
  63. Rotondo, John A. 1984. Clustering analysis of subject partitions of text. Discourse Processes, 7:69-88. find
  64. Song, Fei and Robin Cohen. 1991. Tense interpretation in the context of narrative. In Proceedings of the 9th AAAI, pages 131-136. find
  65. Stifleman, Lisa J. 1995. A discourse analysis approach to structured speech. In AAAI 1995 Spring Symposium Series: Empirical Methods in Discourse Interpretation and Generation, pages 162-167. find
  66. Swerts, Marc. 1995. Combining statistical and phonetic analyses of spontaneous discourse segmentation. In Proceedings of the 12th International Congress of Phonetic Sciences (ICPhS 95), volume 4, pages 208-211. find
  67. Swerts, Marc and Mari Ostendorf. 1995. Discourse prosody in human-machine interactions. In ESCA Workshop on Spoken Dialogue Systems, pages 205-208. find
  68. Walker, Marilyn A. 1995. Limited attention and discourse structure. Computational Linguistics, 22(2):255-264. find
  69. Walker, Marilyn and Steve Whittaker. 1990. Mixed initiative in dialogue: An investigation into discourse segmentation. find
  70. In Proceedings of the 28th Annual Meeting, pages 70-78. Association for Computational Linguistics. find
  71. Webber, Bonnie L. 1988. Tense as discourse anaphor. Computational Linguistics, 14:113-122. find
  72. Webber, Bonnie L. 1991. Structure and ostension in the interpretation of discourse deixis. Language and Cognitive Processes, 6.2:107-135. find
  73. Weiss, Sholom M. and Casimir Kulikowski. 1991. Computer Systems that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems. Morgan Kaufmann. find
  74. Whittaker, Steve and Phil Stenton. 1988. Cues and control in expert-client dialogues. In Proceedings of the 26th Annu'al Meeting, pages 123-130. Association for Computational Linguistics. find
  75. Wightman, Colin W. and Mari Ostendorf. 1994. Automatic labeling of prosodic patterns. IEEE Transactions on Speech and Audio Processing, 2(4):469-481, October. find
  76. Youmans, Gilbert. 1991. A new tool for discourse analysis: The vocabulary management profile. Language, 67(4):763-790. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/passonneau-1997-discourse-segmentation-human-automated-means/