Elamur Research⌕
☰
home / papers / 1988 / An Architecture for Anaphora Resolution

An Architecture for Anaphora Resolution

Summary

Rich and LuperFoy (MCC) describe the pronoun resolution component of Lucy, a prototype portable English front end for knowledge-based systems. Their starting point is that many partial accounts of anaphora exist, from agreement rules to focus-based pragmatics, but none is complete. Instead of committing to one theory, they propose a blackboard-style architecture. Independent modules called constraint sources (CSs) each encode one partial theory. They share a common core discourse structure, which holds referents and the assertions about them. A central handler collects the candidate antecedents each module proposes, has the other modules score them, and settles disagreements. Early versions combined scores by simple averaging, which proved unstable. The authors replaced this with a confidence-weighted combination, so a module can effectively abstain. The paper offers no quantitative evaluation. Instead, it illustrates the system with an annotated trace of a short two-sentence discourse. The main contribution is a theory-neutral framework for testing competing accounts of anaphora inside one working resolver. The authors relate it to the critic-based scope assignment in TEAM.

Key points

  • Structure of a constraint source: each CS bundles up to four functions: modeller, constraint poster, proposer and evaluator. Any of these may be a no-op.
  • Constraint sources implemented: recency, number, gender, animacy, disjoint reference, cataphora, global focus, semantic consistency, type and identity.
  • Ordering for efficiency: recency runs first and proposes generously, drawing on the two prior sentences plus left context. Cheap agreement filters run next to prune candidates early.
  • Scoring scheme:
    • Each CS returns a score from -5 to +5 and a confidence from 0 to 1.
    • Scores are averaged with confidence as the weight, so a confidence of 0 means no opinion.
    • An antecedent is asserted only if it leads the runner-up by more than δ = 0.5.
  • When no candidate clearly wins: the pronoun is left unresolved, producing a partial interpretation, or the user is asked to disambiguate.

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: Coreference resolution

Cited by

26 papers of our library cite it (of the 140673 whose bibliographies we read); 11 of them have a page here, 15 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/974235.974239

@inproceedings{rich1988architecture,
  title = {{An Architecture for Anaphora Resolution}},
  author = {Rich, Elaine and LuperFoy, Susann},
  booktitle = {Second Conference on Applied Natural Language Processing},
  year = {1988},
  doi = {10.3115/974235.974239},
  url = {https://doi.org/10.3115/974235.974239}
}

References

12 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Brennan, S. E., M. W. Friedman, & C. J. Pollard. (1987). A Centering Approach to Pronouns. Proceedings ACL. . find
  2. Cohen, R. R. (1985). Heuristic Reasoning about Uncertainty: An Artificia/ Intelligence Approach. Boston: Pitman Advanced Publishing Program. find
  3. Erman, L. D., P. E. London, & S. F. Fickas. (1981). The Design and an Example Use of Hearsay II1. Proc. IJCAI 7 . . find
  4. Grosz, B. J. (1977). The Representation and Use of Focus in a System for Understanding Dialogs. IJCAI 5 . . find
  5. Grosz, B. J., A. K. Joshi, & S. Weinstein. (1986). Towards a Computational Theory of Discourse Interpretation. find
  6. Grosz, B. J., D. E. Appelt, P. A. Martin, & F. C. N. Pereira. (May 1987). TEAM: An Experiment in the Design of Transportable Natural-Language Interfaces. Artificial Intelligence, 32(2), 173-243. find
  7. Guindon, R., P. Sladky, H. Brunner & J. Conner. (1986). The Structure of User-Advisor Dialogues: Is there Method in their Madness? Proceedings of the 24th Meeting of the Association for Computational Linguistics.. find
  8. Hobbs,J. R. (1978). Resolving References. Lingua, 44, 311-338. find
  9. Pronoun Hobbs, J. R. (1985). On the Coherence and Structure of Discourse (Tech. Rep.). CSLI-85-37, Kamp, H. (1981). A Theory of Truth and Semantic Representation. In J. Froenendijk, T. Janssen, & M. Stokhof (Eds.), Formal Methods in the Study of Language, Part I. Amsterdam, The Netherlands: Mathemat… find
  10. Reinhart, T. (1983). Anaphora and Semantic Interpretation. Chicago, Ill.: University of Chicago Press. find
  11. Rich, E. A., J. Barnett, K. Wittenburg & D. Wroblewski. (1987). Ambiguity Procrastination. Proceedings AAA187. . find
  12. Wittenburg, K. (1986). A Parser for Portable NL Interfaces Using Graph-Unification-Based Grammars. Proceedings AAA186. . 2,4 find

↑ back to top