Elamur Research⌕
☰
home / papers / 1993 / Empirical Studies on the Disambiguation of Cue Phrases

Empirical Studies on the Disambiguation of Cue Phrases

Paper · 1993 · Julia Hirschberg and Diane Litman

Summary

Hirschberg and Litman study how listeners and readers tell apart the two roles of cue phrases such as now, well, say or incidentally. These words can signal discourse structure, for example a topic shift or a digression, or they can act as ordinary sentential elements like temporal adverbs. Earlier systems mostly assumed that discourse uses come clause-initially. The authors show that this assumption is unreliable.

They used two recorded and transcribed corpora:

  • HG82, a multi-speaker radio call-in show, used for an initial study of now and well;
  • RJB86, a 75-minute keynote talk by Ronald Brachman, in which every cue phrase was analysed.

They coded prosodic features using Pierrehumbert's intonation framework, along with text-based cues. Discourse uses turned out to be predictable from intonational phrasing and pitch accent, which the authors capture in a small set of prosodic models. Orthography and part of speech serve as text-side predictors. The work matters because it shows that cue phrase disambiguation is feasible, which supports discourse theories that depend on it. It also has a practical payoff: the findings were built into the Bell Labs Text-to-Speech System.

Key points

  • Prosodic models:
    • Discourse Model A: the cue phrase forms its own intermediate phrase.
    • Discourse Model B: the cue phrase is first in a larger phrase and is either deaccented or carries L*.
    • Sentential Model A: the cue phrase is first in phrase and carries H* or a complex accent.
    • Sentential Model B: the cue phrase is not first in its phrase.
  • Text cues: In RJB86, orthographic cues from the transcription correctly separated discourse from sentential uses in 675 of 843 cases (80.1%). Part of speech was weaker, at 561 of 878 (63.9%). Combining the two barely improved on orthography alone, giving 677 of 843 (80.3%).
  • Hard-to-classify tokens: Annotators could not agree on 75 tokens in RJB86. Of these, 55 (73.3%) fell under Discourse Model B or Sentential Model A, the two models that differ only in accent type. This suggests that accent distinctions are weaker cues than phrasing.
  • Interpretation of the models: Deaccented discourse cues seem to behave like function words, carrying structure rather than content. An L* accent may mark material that is salient but not meant to enter the speakers' shared beliefs.

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

🏢AT&TBedminster · United States29 works · 15,393 citations

📚 Shelves 6 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works Psychology · 798 works Experimental and Cognitive Psychology · 463 works

Cite

Cite as Julia Hirschberg and Diane Litman. 1993. Empirical Studies on the Disambiguation of Cue Phrases. Computational Linguistics.

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

@article{hirschberg1993empirical,
  title = {{Empirical Studies on the Disambiguation of Cue Phrases}},
  author = {Julia Hirschberg and Diane Litman},
  journal = {Computational Linguistics},
  year = {1993},
  doi = {10.7916/d8pv6tgb},
  url = {https://doi.org/10.7916/d8pv6tgb}
}

References

40 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Altenberg, Bengt (1987). Prosodic Patterns in Spoken English: Studies in the Correlation between Prosody and Grammar for Text-to-Speech Conversion, Lund Studies in English, Volume 76. Lund University Press. find
  2. Beckman, M., and Pierrehumbert, J. (1986). "Intonational structure in Japanese and English." Phonology Yearbook, 3, 15-70. find
  3. Bolinger, Dwight (1989). Intonation and Its Uses: Melody in Grammar and Discourse. Edward Arnold. find
  4. Brazil, D., Coulthard, M., and Johns, C. (1980). Discourse Intonation and Language Teaching. Longman. find
  5. Butterworth, B. (1975). "Hesitation and semantic planning in speech." Journal of Psycholinguistic Research, 4, 75-87. find
  6. Church, K. W. (1988). "A stochastic parts program and noun phrase parser for unrestricted text." In Proceedings, Second Conference on Applied Natural Language Processing, Texas, 136-143. our card
  7. Cohen, Robin (1984). "A computational theory of the function of clue words in argument understanding." In Proceedings of 1984 International Computational Linguistics Conference. California, 251-255. find
  8. Francis, W. Nelson, and Ku~era, Henry (1982). Frequency Analysis of English Usage. Houghton Mifflin. find
  9. Grosz, Barbara J., and Sidner, Candace L. (1986). "Attention, intentions, and the structure of discourse." Computational Linguistics, 12(3), 175-204. our card
  10. Grosz, Barbara J. (1977). "The representation and use of focus in dialogue understanding." Technical Report 151, SRI International, Menlo Park, CA. find
  11. Halliday, M. A. K., and Hassan, Ruquaiya (1976). Cohesion in English. Longman. find
  12. Hirschberg, Julia, and Litman, Diane (1987). "Now let's talk about now: Identifying cue phrases intonationally." In Proceedings, 25th Annual Meeting of the Association for Computational Linguistics. Stanford, California, 163-171. find
  13. Hirschberg, J., and Pierrehumbert, J. (1986). "The intonational structuring of discourse." In Proceedings, 24th Annual Meeting of the Association for Computational Linguistics. New York, 136-144. find
  14. Hirschberg, J., and Ward, G. (1992). "The influence of pitch range, duration, amplitude, and spectral features on the interpretation of L*+H L I-I%." Journal of Phonetics, 20(2), 241-251. find
  15. Hirschberg, Julia (1991). A Theory of Scalar Implicature. Garland Publishing, Inc. find
  16. Hobbs, J. (1979). "Coherence and coreference." Cognitive Science, 3(1), 67-90. find
  17. Hockey, Beth Ann (1991). Personal communication. find
  18. Litman, Diane J., and Allen, James E (1987). A plan recognition model for subdialogues in conversation. Cognitive Science, 11, 163-200. find
  19. Litman, Diane, and Hirschberg, Julia (1990). "Disambiguating cue phrases in text and speech." In Papers Presented to the 13th International Conference on Computational Linguistics. Helsinki, 251-256. find
  20. Mann, W. C., and Thompson, S. A. (1983). "Relational propositions in discourse." Technical Report ISI/RR-83-115, ISI/USC, November 1983. find
  21. Olive, J. P., and Liberman, M. Y. (1985). "Text to speech — An overview." Journal of the Acoustic Society of America, Suppl. 1, 78, s6. find
  22. Pierrehumbert, J., and Hirschberg, J. (1990). "The meaning of intonational contours in the interpretation of discourse." In Intentions in Communication, edited by P. Cohen, J. Morgan, and M. Pollack. The MIT Press. find
  23. Pierrehumbert, Janet B., and Steele, Shirley (1987). "How many rise-fall-rise contours?" In Proceedings, Eleventh Meeting of the International Congress of Phonetic Sciences. Tallinn. find
  24. Pierrehumbert, Janet B. (1980). The phonology and phonetics of English intonation. Doctoral dissertation, Massachusetts Institute of Technology, September 1980. find
  25. Pollack, M. E.; Hirschberg, J.; and Webber, B. (1982). "User participation in the reasoning processes of expert systems." Technical Report MS-CIS-82-9, University of Pennsylvania, July 1982. find
  26. Prince, E. E (1981). "Toward a taxonomy of given-new information." In Radical Pragmatics, edited by P. Cole, 223-255. Academic Press. find
  27. Quirk, R. (1972). A Grammar of Contemporary English. Longman. find
  28. Reichman, R. (1985). Getting Computers to Talk Like You and Me: Discourse Context, Focus, and Semantics. The MIT Press, Bradford Books. find
  29. Schegloff, E. A. (1979). "The relevance of repair to syntax-for-conversation." In Syntax and Semantics, Volume 12, edited by T. Givon, 261-288. Academic Press. find
  30. Schiffrin, Deborah (1987). Discourse Markers. Cambridge University Press. find
  31. Schourup, Lawrence (1985). Common Discourse Particles in English Conversation. Garland Publishing, Inc. find
  32. Sidner, C. L. (1985). "Plan parsing for intended response recognition in discourse." Computational Intelligence, 1(1), 1-10. find
  33. Silverman, Kim; Beckman, Mary; Pierrehumbert, Janet; Ostendorf, Mari; Wightman, Colin; Price, Patti; and Hirschberg, Julia (1992a). "TOBI: A standard scheme for labeling prosody." In Proceedings, Second International Conference on Spoken Language Processing. find
  34. Silverman, Kim; Blaauw, Eleonora; Spitz, Judith; and Pitrelli, John E (1992b). "Towards using prosody in speech recognition/understanding systems: Differences between read and spontaneous speech." In Proceedings, Fifth DARPA Workshop on Speech and Natural Language. find
  35. Silverman, K. (1987). The structure and processing of fundamental frequency contours. Doctoral dissertation, Cambridge University, Cambridge, UK. find
  36. Sproat, R.; Hirschberg, J.; and Yarowsky, D. (1992). "A corpus-based synthesizer." In Proceedings, International Conference on Spoken Language Processing. find
  37. Swora, Maria G., and Beckman, Mary E. (1991). "The intonation of cue words in task-oriented dialogues." Presented at the LSA Annual Meeting, Chicago, Illinois, January 1991. find
  38. Talkin, David (1989). "Looking at speech." Speech Technology, 4, 74-77. find
  39. Warner, Richard G. (1985). Discourse Connectives in English. Garland Publishing, Inc. find
  40. Zuckerman, Ingrid, and Pearl, Judea (1986). "Comprehension-driven generation of meta-technical utterances in math tutoring." In Proceedings, Fifth National Conference of the AAAI. Philadelphia, PA, 606-611. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hirschberg-1993-empirical-studies-disambiguation-cue-phrases/