Elamur Research⌕
☰
home / papers / 2004 / An Algorithm for Resolving Individual and Abstract Anaphora in Danish Texts and Dialogues

An Algorithm for Resolving Individual and Abstract Anaphora in Danish Texts and Dialogues

Summary

The paper presents dar, a rule-based algorithm for resolving intersentential pronouns in Danish. It covers pronouns with nominal antecedents (IPAs) and pronouns pointing to abstract entities evoked by clauses, verb phrases or longer discourse stretches (APAs). Unlike the English systems es00 and phora, it targets both written texts and spoken dialogues.

For individual anaphora, dar treats givenness as the default salience cue. Entities that speakers explicitly mark as focal (through clefts, focusing adverbs, prosody or answers to questions) outrank given ones, and parallelism outranks both. For abstract anaphora, it extends Eckert and Strube's es00 with Danish-specific discrimination rules built partly from the Danish parole lexicon.

The algorithm was evaluated manually on texts (manuals, novels, newspapers) and on three dialogue corpora (sl, bysoc, pid). On individual pronouns it clearly outperformed the bfp, str98 and es00 baselines. Its results on abstract pronouns were only moderately better than es00. The work shows that focus-aware salience modelling helps anaphora resolution and that es00-style abstract-anaphor handling carries over to Danish and to written text.

Key points

  • Abstract anaphors are frequent in Danish: 15% of pronominal anaphors in texts and 48% in dialogues. Neuter singular pronouns were abstract in about two-thirds of cases.
  • The preference interaction model is ordered Parallelism ⊇ Focality ⊇ Pronominal chain ⊇ Givenness. It also distinguishes weak (unstressed) from strong (stressed or demonstrative) pronouns.
  • On texts, ResolveIpa reached 88.33 precision and 89.14 recall, compared with 79.53 for bfp and 81.24 for str98. Full dar on texts scored 86.02/86.82 (P/R) for IPAs and 72.41/81.82 for APAs.
  • On dialogues, dar beat es00 in F-measure for IPAs (71.71 vs 62.48) and for APAs (69.13 vs 64.5).
  • Removing the predefined dialogue structure dropped success rates to 60.1% for IPAs and 39.3% for APAs. Remaining errors stem largely from missing commonsense knowledge, distant antecedents and vague anaphors.

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

4 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 1 not yet.

Cite

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

@inproceedings{navarretta2004algorithm,
  title = {{An Algorithm for Resolving Individual and Abstract Anaphora in Danish Texts and Dialogues}},
  author = {Navarretta, Costanza},
  booktitle = {Proceedings of the Conference on Reference Resolution and Its Applications},
  year = {2004},
  url = {https://aclanthology.org/W04-0713/}
}

References

24 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. A. Braasch, C. Navarretta, and N.H. Sørensen. 1998. Danish lexicon documentation. Technical Report LE-PAROLE. WP3.3-CST, CST. find
  2. S. F. Brennan, M. W. Friedman, and C. J. Pollard. 1987. A Centering Approach to Pronouns. In Proceedings of the 25th Annual Meeting of the Association for Computational Linguistics (ACL’87), pages 155–162, California, USA. Stanford University. find
  3. D. Byron and J. Allen. 1998. Resolving Demonstrative Pronouns in the TRAINS93 corpus. In Proceedings of the Second Colloquium on Discourse Anaphora and Anaphor Resolution (DAARC 2), pages 68–81. find
  4. D. K. Byron. 2002. Resolving Pronominal Reference to Abstract Entities. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL 2002). find
  5. J. Carletta. 1996. Assessing agreement on classification tasks. the kappa statistic. Computational Linguistics, 22(2):249–254. ↗ our card
  6. D. Duncker and J. Hermann. 1996. Pa-tientord og lægeord - særord eller fælle-sord? Månedsskrift for Praktisk Lægegern-ing - Tidsskrift for Praktiserende Lægers Efteruddannelse, pages 1019–1030. find
  7. M. Eckert and M. Strube. 2000. Dialogue acts, synchronising units and anaphora resolution. Journal of Semantics, 17:51–89. find
  8. F. Gregersen and I. L. Pedersen, editors. 1991. The Copenhagen study in urban sociolinguistics. Reitzel. find
  9. B. J. Grosz and C. L. Sidner. 1986. Attention, Intentions, and the Structure of Discourse. Computational Linguistics, 12(3):175–284. ↗ our card
  10. B. Grosz, A. K. Joshi, and S. Weinstein. 1995. Centering:A Framework for Modeling the Local Coherence of Discourse. Computational Linguistics, 21(2):203–225. find our card
  11. J. K. Gundel, N. Hedberg, and R. Zacharski. 1993. Cognitive status and the form of referring expressions in discourse. Language, 69(2):274–307. ↗
  12. E. Hajičová, P. Kuboň, and V. Kuboň. 1990. Hierarchy of Salience and Discourse Analysis and Production. In H. Karlgren, editor, Proceedings of the 13th International Conference on Computational Linguistics (COLING’90), volume III, pages 144–148, Helsinki. find
  13. J. R. Hobbs. 1983. Why Is Discourse Coherent? In Fritz Neubauer, editor, Coherence In Natural-Language Texts, volume 38 of Papers in Textlinguistics, pages 29–70. Helmut Buske Verlag Hamburg. find
  14. K. A. Jensen. 1989. Projekt invandrerdansk. Technical report, Copenhagen University. find
  15. M. Kameyama. 1996. Indefeasible Semantics and Defeasible Pragmatics. In M. Kanazawa, C. Piñon, and H. de Stwart, editors, Quantifiers, Deduction and Context, pages 111–138. CSLI, Stanford, CA. ↗
  16. C. Navarretta. 1997. Encoding Danish Verbs in the PAROLE Model. In R. Mitkov, N. Nicolov, and N. Nikolov, editors, Proceedings of RANLP’97.Recent Advances in Natural Language Processing, pages 359–363, Tzigov Chark, Bulgaria. find
  17. C. Navarretta. 2002a. Combining Information Structure and Centering-based Models of Salience for Resolving Intersentential Pronominal Anaphora. In A. Branco, T. McEnery, and R.Mitkov, editors, Proceedings of the 4th Discourse Anaphora and Anaphora Resolution Colloqium, pages 135– 140. Ediçoes Colibri. find
  18. E. F. Prince. 1981. Toward a taxonomy of given-new information. In P. Cole, editor, Radical Pragmatics, pages 223–255. Academic Press. find
  19. P. Sgall, E. Hajic̆ová, and J. Panevová. 1986. The Meaning of the Sentence in its Semantic and Pragmatic Aspects. Reidel, Dordrecht. find
  20. C. Sidner. 1983. Focusing in the Comprehension of Definite Anaphora. In M. Brady and R. Berwick, editors, Computational Models of Discourse, pages 267–330. MIT Press. find
  21. M. Strube and U. Hahn. 1996. Functional Centering. In Proceedings of the 34th International Conference on Computational Linguistics (ACL’96), pages 270–277, Ca. find
  22. M. Strube and C. Müller. 2003. A machine learning approach to pronoun resolution in spoken dialogue. In Proceedings of the ACL’03, pages 168–175. find our card
  23. M. Strube. 1998. Never Look Back: An Alternative to Centering. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (COLING-ACL’98), volume II, pages 1251–1257. ↗
  24. B. L. Webber. 1991. Structure and Ostension in the Interpretation of Discourse Deixis. Natural Language and Cognitive Processes, 6(2):107–135, January. ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/navarretta-2004-algorithm-resolving-individual-abstract-anaphora/