Elamur Research⌕
☰
home / papers / 1999 / Generating Anaphoric Expressions: Pronoun or Definite Description?

Generating Anaphoric Expressions: Pronoun or Definite Description?

Summary

The paper addresses a practical question in natural language generation: when a system refers back to an entity, should it produce a pronoun or a fuller definite description (a definite noun phrase or a name)? Earlier generation work relied mainly on referent accessibility or focus, typically using a pronoun when the same entity stays central. The authors show that this does not match real usage. They analysed New York Times news articles and proposed rules covering several factors: whether the mention falls in the same sentence, how far back the previous mention is, discourse structure, and ambiguity. For discourse structure they introduce "discourse threads". In news text, threads are defined by the time a clause refers to. A change of time favours a definite description even when a pronoun would be unambiguous. The resulting algorithm matched the writers' choices in about 85% of cases. This matters because threads can be derived from input that any sentence generator already has, unlike vaguely defined discourse segments.

Key points

  • Data: New York Times news articles. The authors note that their long, complex sentences differ from those in earlier pronoun-generating systems.
  • Factors proposed:
    • Pronouns are preferred for repeat mentions within one sentence.
    • Definite descriptions are preferred when the last mention is several sentences back.
    • Pronouns are preferred if the entity's last mention occurred within the current thread.
    • A pronoun should only be used if it can be resolved correctly.
  • Time analysis: The analysis distinguishes four types of time, cued by temporal adverbials and tense changes.
  • Prior approaches judged insufficient: focus-based rules, Dale (1992), centering Rule 1 and transition preferences, and Passonneau (1996). Passonneau's approach needs externally supplied segment boundaries.
  • Limitations and future work: The time-change rule produces too many definite descriptions. Following Vonk et al. (1992), the authors plan to check whether other boundary markers, such as preposed adverbials, explain this. They also plan reading-time or comprehension experiments as an alternative to evaluating by matching human-written text.

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 · Coreference resolution

Cited by

24 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 23 not yet.

Cite

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

@inproceedings{mccoy1999generating,
  title = {{Generating Anaphoric Expressions: Pronoun or Definite Description?}},
  author = {McCoy, Kathleen E. and Strube, Michael},
  booktitle = {The Relation of Discourse/Dialogue Structure and Reference},
  year = {1999},
  url = {https://aclanthology.org/W99-0108/}
}

References

28 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Appelt, D. E. (1981). P/arming Natural-Language Utterances to Satisfy Multiple Goals, (Ph.D. thesis). Stanford University. Also appeared as: SRI International Technical Note 259, March 1982. find
  2. Appelt, D. E. (1985). Planning English referring expressions. Ani~cial Intelligence, 26(1): 1-33. find
  3. Arnold, J. E. (1998). Reference Form and Discourse Patterns, (Ph.D. thesis). Stanford University, Department of Linguistics. find
  4. Brennan, S. E., M. W. Friedman & C. J. Pollard (1987). A centerin.g approach to pronouns. In Proceedings • of the 2Y m Annual Meeting of the Association for Computot/ona/Linguis6c$, Stanford, Cal., 6.-9 July !987, pp. !55-162. find
  5. Dale, R. (1992). Genera~nf Referring E, rpressions: Constructing Descriptions in a Domain of Objects and Processes. Cambridge, Mass.: Mrr Press. find
  6. Dale, It. & E. Reiter (1995). Computational interpretations of the Gricean maxims in the generation of referring expressions. Cognitive Science, 18:233-- 263. find our card
  7. Oenette, G. (1980). Narrative Discourse: An Fasay in Method. Ithaca, N.Y.: Cornell University Press. find
  8. Givou, T. (1983). Topic continuity in spoken English. In T. Given ted.), Topic Continuity in Discourse: A Quantitative Cross-Language Study. Amsterdam, Philadelphia: John Benjamins. find
  9. Gordon, P. C. & R. Hendrick (1998). The representation and processing of coreference in discourse. Cognitive Science, 22(4):389--424. find
  10. Grosz, B. J.o A. K. Joshi & S. Weinstein (1995). Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203-225. @ 0 0 @ @ @ @ 0 O 0 @ @ @ 0 0 0 @ @ 0 0 0 @ 0 0 0 @ 0 @ @ 0 0 0 0 0 0 @ Grosz, B. J. & C. L. Sidner (1986). Attention, intentions, and the… find our card
  11. Kameyama, M. (1998). lntrasentential centering: A case study. In M. Walker, A. Joshi & E. Prince (Eds.), Centering Theory in Discourse, pp. 89-112. Oxford, U.IL: Oxford University Press. find
  12. Mann, W. C. & S. A. Thompson (1988). Rhetorical structure theory. Toward a functional theory of text organization. Text, 8(3):243-281. find our card
  13. McDonald, D. D. (1980). Natural Language Production as a Process of Decision Mata'ng Under Constraint, (Ph.D. thesis). MIT. • McKeown, K. R. (1983). Focus constraints on language generation. In Proceedings of the 8 th International Joint Conference on Artificial Intelligence, Karlsruhe, Germany, Aug… find
  14. McKeown, IL IL (1985). Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge, U.K.: Cambridge University Press. find
  15. Moens, M. & M. Steedman (1988). Temporal ontology and temporal reference. Computational Linguistics, 14(2):15-28. find
  16. Nakhimovsky, Ao (1988). Aspect, aspoctual class, and the temporal structure of narrative. Computational Linguistics, 14(2):29-43. find
  17. Passonneau, R. (1996). Using centering to relax Gricean constraints on disocursz anaphoric noun ophrase~ Language and Speech, 39(2):229-264. find
  18. Prince, G. (1982), Narratology: The Form and Function. ing of Narrative. Berlin: Mouton. find
  19. Reichman, R. (1985). Getting Computen to Talk like You andMe. Cambridge, Mass.: MIT Press. find
  20. Reiter, E. (1990). Generating descriptions that exploit a user's domain knowledge. In R. Dale, C. Mellish & M. Zock (Eds.), Current Research in Natural Language Generation. London: Academic Press. find
  21. Ros6, C. P., B. DiEngenio, L. S. Levin & C. Van Ess-Dykema (1995). Discourse processing of dialogues with multiple threads. In Proceedings of the 33 rd Annual Meeting of the Association for Computational Linguixtics, Cambridge, Mass., 26-30 June 1995, pp. 31-38. find
  22. D 0 0 0 0 @ 0 0 0 0 0 @ @ 0 0 0 @ @ 0 @ @ 0 0 0 0 0 0 0 0 @ 0 0 0 0 0 0 @ Sidner, C. L. (1979). Towards a Computational Theory of Definite Anaphora Comprehension in English. Technical Report AJ-Memo 537, Cambridge, Mass.: Massachusetts Institute of Technology. AI Lab. find
  23. Strube, M. (1998). Never look back: An alternative to centering. In Proceedings of the 17 th International Conference on Computational Linguistics and 36 th Annual Meeting of the Association for Computational Linguistics, Montr~.ad, Quebec, Canada, I0-14 August 1998, Vol. 2, pp. 1251-1257. find
  24. StTube, M. & U. Hahn (1997). Centered segmentation: Scaling up the centering model to global referential discourse structure. In Proceedings of the 19 th Annual Conference of the Cognitive Science Society, Palo Alto, Cal., 7-10 August 1997. find
  25. Suri, L. 7_, & K. F. McCoy (1994). RAFT/RAPR and centering: A comparison and discussion of problems related to processing complex sentences. Computational Linguistics, 20(2):301-317. find
  26. Vogt, J. (1990). Aspekte erzllhlender Prosa: Eine Einfllhrung in Erzilhltechnik and Romantheorie (7 ta ed.). Opladen: Westdeutscher Verlag. find
  27. Vonk, W., L. G. Hustinx & W. H. Simons (1992). The use of referential expressions in structuring discourse. Language and Cognitive Processes, 7(3/4):301-333~ Webber, B. L. (1991). Structure and ostension in the interpretation of discourse deixis. Language and Cognitive Processes, 6(2):107-135. find
  28. Wiobe, J. M. (1994). Tracking point of view in narrative. Computational Linguistics, 20(2):233-287. find

↑ back to top

This page in Markdown →