Elamur Research⌕
☰
home / papers / 2000 / Rhetorical Structure in Dialog

Rhetorical Structure in Dialog

Summary

The paper reports on an early effort to apply Rhetorical Structure Theory (RST) to complex, mixed-initiative, task-oriented spoken dialog. The goal is to support content planning for conversational agents such as the TRIPS system. The author's pilot study annotated one dialog from the Monroe corpus. Two annotators worked independently with O'Donnell's RST tool, using Mann and Thompson's relations plus some dialog- and domain-specific ones. Their tree structures largely agreed, but their relation labels diverged sharply. Neither annotation covered the whole dialog, and some observed structure fit no available relation.

In response, the pilot was halted and a new annotation scheme for "argumentation acts" was designed. The scheme does four things:

  • It guides annotators with decision trees, simplified definitions, examples and discourse cues.
  • It drops overly broad relations.
  • It adds adjacency-pair relations that may cross turns.
  • It labels presentational and subject-matter relations separately, together with content types.

The work matters because rhetorical goals, not only task goals, explain many contributions in dialog. Turn-internal analysis or existing dialog schemes miss this structure.

Key points

  • Corpora: the Monroe corpus is the main target, with reference to TRAINS and the HCRC Maptask corpus. The annotation manual is being refined on TRAINS-93 dialogs.
  • Pilot problems: the motivate/justify and elaboration/motivation distinctions were ambiguous, and elaboration and joint were too broad. In the new scheme, joint is removed and elaboration is replaced by finer subtypes.
  • Adjacency pairs such as question-answer and proposal-accept become relations. They can be bi-nuclear and can span multiple turns. Other relations, such as elaboration and sequence, may also cross speakers.
  • Annotators may mark three things for a span: a presentational relation, a subject-matter relation, and a content type (e.g., time, location, number). This departs from Mann and Thompson's rule that subject-matter relations take precedence.
  • In 8 DAMSL-tagged dialogs, 40% of utterances were statements. The author argues this justifies modeling rhetorical structure separately, unlike DAMSL, the Maptask scheme or COCONUT.

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

Fields: Linguistics & languages

Topics: Discourse analysis

Cited by

10 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/1118253.1118288

@inproceedings{stent2000rhetorical,
  title = {{Rhetorical Structure in Dialog}},
  author = {Stent, Amanda},
  booktitle = {INLG'2000 Proceedings of the First International Conference on Natural Language Generation},
  year = {2000},
  doi = {10.3115/1118253.1118288},
  url = {https://doi.org/10.3115/1118253.1118288}
}

References

22 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. J. Allen, D. Byron, M. Dzikovska, G. Ferguson, L. Galescu, and A. Stent. 2000. An architecture for a generic dialogue shell, upcoming in the Natural Language Engineering Journal special issue on Best Practices in Spoken Language Dialogue Systems Engineering. find
  2. A. Anderson, M. Bader, E. Bard, E. Boyle, G. Doherty, S. Garrod, S. Isard, J. Kowtko, J. MeAl-lister, J. Miller, C. Sotillo, H. Thompson, and R. Weinert. 1991. The HCRC Maptask corpus. Language and Speech, 34:351-366. find
  3. J. Carletta, A. Isard, S. Isard, J. Kowtko, and G. Doherty-Sneddon. 1996. HCRC dialog structure coding manual. Technical Report HCRC/TR-82, HCRC, Edinburgh University. find
  4. A. Cawsey. 1993. Planning interactive explanations. International Journal of Man-Machine Studies, 38:169-199. find
  5. H. Clark. 1996. Using Language. Cambridge University Press. find
  6. M. Core and J. Allen. 1997. Coding dialogs with the DAMSL annotation scheme. In AAAI Fall Symposium on Communicative Action in Humans and Machines, pages 28-35, November. find
  7. B. DiEugenio, P. Jordan. and L. Pylkkiinen. 1998. The COCONUT project: Dialogue annotation manual. Technical Report 98-I, ISP, University of Pittsburgh. find
  8. B. Gross- and C. Sidner. 1986. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3). find our card
  9. P. Heeman and J. Allen. 1995. The TRAINS-93 dialogs. Technical Report Trains TN 94-2, Computer Science Dept., U. Rochester, March. find
  10. E. Hovy. 1993. Automated discourse generation using discourse structure relations. Artificial Intelligence, 63(1-2):341-385. W.. Mann_and S. Thompsom 19877. Rhetorical structure theow: a theory o f text organisation. In L. Polanyi, editor, The Structure of Discourse. find
  11. Ablex, Norwood, NJ. D. Marcu. 1997. The rhetorical parsing, summarization, and generation of natural language texts. Technical Report CSRG-371, Department of Computer Science, University of Toronto. find
  12. D. Marcu. 1999. A formal and computational synthesis of Grosz and Sidner's and Mann and Thompson's theories. In The Workshop on Levels of Representation in Discourse, Edinburgh, Scotland. find
  13. K. McKeown. 1985. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. find
  14. Cambridge University Press, Cambridge. J. Moore and C. Paris. 1992. Exploiting user feedback to compensate for the unreliability of user models. UMUAI, 2(4):331-365. find
  15. J. D. Moore and C. L. Paris. 1993. Planning text for advisory dialogues: Capturing intentional and rhetorical information. Computational Linguistics, 19(4):651-695. find
  16. J. Moore and M. Pollack. 1992. A problem for RST: The need for multi-level discourse analysis. Computational Linguistics, 18(4):537-544. find
  17. M. G. Moser and J. D. Moore. 1996. Toward a synthesis of two accounts of discourse structure. Computational Linguistics, 22(3):409-420. find
  18. M. Moser, J. Moore, and E. Glendening. 1996. Instructions for coding explanations: Identifying segments, relations and minimal units. Technical Report 96-17, University of Pittsburgh. Department of Computer Science. find
  19. C. Nakatani and D. Traum. 1999. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University, of Maryland. find
  20. Michael O'Donnell. 1997. RST-Tool: An RST analysis tool. In Proceedings of the 6th European Workshop on Natural Language Generation, Gerhard-Mercator University, Duisburg, Germany. find
  21. A. Stent. 2000. The Monroe corpus. Technical Report TR728/TN99-2, University of Rochester. find
  22. D. Traum and E. Hinkehnan. 1992. Conversation acts in task-oriented spoken dialogue. Computational Intelli.qenee, 8(3):575--599. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/stent-2000-rhetorical-structure-dialog/