Elamur Research⌕
☰
home / papers / 2000 / An Empirically-based System for Processing Definite Descriptions

An Empirically-based System for Processing Definite Descriptions

Paper · 2000 · Renata Vieira and Massimo Poesio

Summary

Most computational models treat definite descriptions (noun phrases with the) mainly as anaphors that must be linked to an earlier antecedent. Vieira and Poesio had previously annotated Wall Street Journal texts and found that about half of these descriptions actually introduce new entities. Building on that study, they built a domain-independent system that treats recognising discourse-new descriptions as being as important as resolving anaphoric ones.

The system deliberately avoids hand-encoded inference. It relies only on:

  • syntactic structure,
  • lexical relations from WordNet,
  • a small amount of general hand-coded knowledge,
  • information that can be learned from corpora.

Its heuristics cover antecedent matching, discourse segmentation, discourse-new detection and suggesting anchors for bridging descriptions. The authors tested it on the annotated corpus, split into a development part and a held-out test part. They scored it in two ways: precision/recall against a MUC-style gold standard, and K agreement with the human annotators.

Same-head (direct) anaphora is the easiest case for this shallow approach. Bridging gives by far the weakest results and many false positives. The work matters because it sets a measurable baseline showing where richer lexical or commonsense knowledge is really needed.

Key points

  • Data: a subset of the Penn Treebank I (Wall Street Journal articles). Corpus 1 has about 1,000 definite descriptions and was used for development; Corpus 2 has about 400 and was reserved for testing.
  • Definite descriptions fall into three classes: direct anaphora, bridging descriptions and discourse-new descriptions. Roughly half of all descriptions in the corpus are discourse-new.
  • Human agreement was K = 0.76 for the first-mention vs. subsequent-mention distinction and K = 0.73 for the three-way classification.
  • Resources include WordNet for lexical relations. Planned extensions include running the system on output from Abney's CASS parser and adding local focus-tracking mechanisms to reduce bridging false positives.
  • Open problems the authors name:
    • automatically acquiring knowledge about how nouns and adjectives behave,
    • handling pre- and postmodification, which was frequent among discourse-new descriptions and a source of annotator disagreement,
    • access to encyclopedic knowledge.

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

🎓University of EdinburghEdinburgh · United Kingdom255 works · 68,771 citations

Also on the byline: Universidade do Vale do Rio dos Sinos.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,085 worksArtificial Intelligence · 8,888 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Coreference resolution · 550 works

Cite

Cite as Renata Vieira and Massimo Poesio. 2000. An Empirically-based System for Processing Definite Descriptions. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/089120100750105948

@article{vieira2000empirically,
  title = {{An Empirically-based System for Processing Definite Descriptions}},
  author = {Renata Vieira and Massimo Poesio},
  journal = {Computational Linguistics},
  year = {2000},
  doi = {10.1162/089120100750105948},
  url = {https://doi.org/10.1162/089120100750105948}
}

References

83 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abney, Steve. 1991. Parsing by chunks. In R. Berwick, S. Abney, and C. Tenny, editors, Principle-based Parsing. Kluwer, Dordrecht, pages 257-278. find
  2. Alshawi, Hiyan. 1987. Memory and Context for Language Interpretation. Cambridge University Press, Cambridge. find
  3. Alshawi, Hiyan. 1990. Resolving quasiqogical forms. Computational Linguistics, 16(3):133-144. find
  4. Alshawi, Hiyan, editor. 1992. The Core Language Engine. MIT Press, Cambridge, MA. find
  5. Aone, Chinatsu and Scott W. Bennett. 1995. Automated acquisition of anaphora resolution strategies. In Proceedings of the AAAI Spring Symposium on Empirical Methods in Discourse Interpretation and Generation, pages 1-7, Stanford. find
  6. Appelt, Douglas, Jerry R. Hobbs, John Bear, David Israel, Megumi Kameyama, Andy Kehler, David Martin, Karen Myers, and Mabry Tyson. 1995. SRI International FASTUS system MUC-6 test results and analysis. In Proc. of the Sixth Message Understanding Conference, pages 237-248, Columbia, MD, November. find
  7. Azzam, Saliha, Kevin Humphreys, and Robert Gaizauskas. 1998. Evaluating a focus-based approach to anaphora resolution. In COLING-ACL "98: 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 74-78, Montreal, Qu…
  8. Bean, David L. and Ellen Riloff. 1999. Corpus-based identification of non-anaphoric noun phrases. In Proceedings of the 37th Annual Meeting, pages 373-380, University of Maryland. Association for Computational Linguistics.
  9. Bikel, Daniel, Scott Miller, Richard Schwartz, and Ralph Weischedel. 1997. Nymble: A high-performance learning name finder. In Proceedings of the 5th Conference on Applied Natural Language Processing, pages 194-201, Washington, DC Association for Computational Linguistics.
  10. Bosch, Peter and Bart Geurts. 1989. Processing definite NPs. IWBS Report 78, IBM Germany, July. find
  11. Burger, John D. and Dennis Connolly. 1992. Probabilistic resolution of anaphoric reference. In Proceedings of the AAAI Fall Symposium on Probabilistic Approaches to Natural Language, pages 17-24, Cambridge, MA. find
  12. Carbonell, Jamie and Ralf D. Brown. 1988. Anaphora resolution: A multi-strategy approach. In Proceedings of the 12th International Conference on Computational Linguistics (COLING-88), pages 96-101, Budapest, Hungary.
  13. Carletta, Jean. 1996. Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22(2):249-254.
  14. Carletta, Jean, Amy Isard, Stephen Isard, Jacqueline C. Kowtko, Gwyneth Doherty-Sneddon, and Anne H. Anderson. 1997. The reliability of a dialogue structure coding scheme. Computational Linguistics, 23(1):13-32.
  15. Carter, David M. 1987. Interpreting Anaphors in Natural Language Texts. Ellis Horwood, Chichester, UK. find
  16. Chinchor, Nancy A. 1995. Statistical significance of MUC-6 results. In Proceedings of the Sixth Message Understanding Conference (MUC-6), pages 39-44, Columbia, MD, November 6-8. find
  17. Chinchor, Nancy A. 1997. Overview of MUC-7/MET-2. In Proceedings of the Seventh Message Understanding Conference (MUC-7). Available at http://www.muc.saic.com/proceedings/ muc_7_proceedings/overview, html. ↗
  18. Cho, Sehyeong and Anthony S. Maida. 1992. Using a Bayesian framework to identify the referents of definite descriptions. In Proceedings of the AAAI Fall Symposium on Probabilistic Approaches to Natural Language, pages 39-46, Cambridge, MA. find
  19. Clark, Herbert H. 1977. Inferences in comprehension. In D. Laberge and S. J. Samuels, editors, Basic Process in Reading: Perception and Comprehension. Lawrence Erlbaum, pages 243-263. find
  20. Clark, Herbert H. and Catherine R. Marshall. 1981. Definite reference and mutual knowledge. In A. Joshi, B. Webber, and I. Sag, editors, Elements of Discourse Understanding. Cambridge University Press, New York. Fellbaum, Christiane, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press,… find
  21. Fox, Barbara A. 1987. Discourse Structure and Anaphora. Cambridge University Press, Cambridge, UK. find
  22. Fraurud, Keri. 1990. Definiteness and the processing of NPs in natural discourse. Journal o/Semantics, 7:395-433. find
  23. Gaizauskas, Robert, Takahiro Wakao, Kevin Humphreys, Hamish Cunningham, and Yorick Wilks. 1995. University of Sheffield: Description of the LaSIE System as used for MUC-6. In Proceedings o/the Sixth Message Understanding Conference (MUC-6), pages 207-220. Morgan Kaufmann. find
  24. Grosz, Barbara J. 1977. The Representation and Use of Focus in Dialogue Understanding. find
  25. Grosz, Barbara J., Aravind K. Joshi, and Scott Weinstein. 1983. Providing a unified account of definite noun phrases in discourse. In Proceedings o/the 21st Annual Meeting, pages 44-50. Association for Computational Linguistics.
  26. Grosz, Barbara. J., Aravind. K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):202-225. (The paper originally appeared as an unpublished manuscript in 1986.).
  27. Grosz, Barbara J. and Candace L. Sidner. 1986. Attention, intention, and the structure of discourse. Computational Linguistics, 12(3):175-204. find
  28. Hahn, Udo; Michael Strube, and Katja Markert. 1996. Bridging textual ellipsis. In COLING '96: Proceedings of the 16th International Conference on Computational Linguistics, pages 496-501, Kopenhagen, Aug 5-9 1996. find
  29. Hardt, Daniel. 1997. An empirical approach to VP ellipsis. Computational Linguistics, 23(4):525-541.
  30. Hatzivassiloglou, Vasileios and Kathleen McKeown. 1993. Towards the automatic identification of adjectival scales: clustering adjectives according to meaning. In Proceedings o/the 31st Annual Meeting, pages 172-182, Ohio State University. Association for Computational Linguistics. find
  31. Hawkins, John A. 1978. DeJiniteness and Indefiniteness. Croom Helm, London. find
  32. Hearst, Marti A. 1997. TextTiling: Segmenting text into multi-paragraph subtopic passages. Computational Linguistics, 23(1):33-64. find
  33. Helm, Irene. 1982. The Semantics o/Definite and Indefinite Noun Phrases. Ph.D. thesis, University of Massachusetts at Amherst. find
  34. Hitzeman, Janet and Massimo Poesio. 1998. find
  35. Long-distance pronominalisation and global focus. In COLING/ACL "98: 36th Annual Meeting of the Association/or Computational Linguistics and 17th International Conference on Computational Linguistics. Volume 1, pages 550-556, Montreal, Quebec, Canada. find
  36. Hobbs, Jerry R., Mark E. Stickel, Douglas A. Appelt, and Paul Martin. 1993. Interpretation as abduction. Arti~cial Intelligence Journal, 63:69-142. find
  37. Humphreys, Kevin, Robert Gaizauskas, Saliha Azzam, Chris Huyck, B. Mitchell, and Hamish Cunningham. 1998. University of Sheffield: Description of the LaSIE-II System as used for MUC-7. In Proceedings of the Seventh Message Understanding Conference (MUC-7). find
  38. Available on the Web at www.muc.saic.com. find
  39. Ishikawa, Tomonori. 1998. Acquisition of associative information and resolution of bridging descriptions. Master's thesis, University of Edinburgh, Department of Linguistics, Edinburgh, Scotland. find
  40. Kameyama, Megumi. 1997. Recognizing referential links: An information extraction perspective. In Proceedings off the ACL Workshop on Operational Factors in Practical, Robust Anaphora Resolution/or Unrestricted Texts, pages 46-53, Madrid, Spain, July. Association for Computational Linguistics. find
  41. Krippendorff, Klaus. 1980. Content Analysis: An Introduction to its Methodology. Sage Publications, Beverly Hills, London. find
  42. Landis, J. R., and G. G. Koch. 1977. The measurement of observer agreement for categorial data. Biometrics, 36:159-174. find
  43. Lappin, Shalom and H. J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535-562.
  44. Lascarides, Alex and Nicholas Ashen 1993. Temporal interpretation, discourse relations and commonsense entailment. Linguistics and Philosophy, 16(5):437-493. find
  45. LObner, Sebastian. 1987. Natural language and generalised quantifier theory. In P. G/irdenfors, editor, Generalized Quantifiers. D. Reidel, Dordrecht, The Netherlands, pages 93-108. find
  46. Mani, Inderjeet and T. Richard MacMillan. 1996. Identifying unknown proper names in newswire text. In Bran Boguraev and James Pustejovsky, editors, Corpus Processing/or Lexical Acquisition. MIT Press, Cambridge, MA, pages 41-59. find
  47. Marcu, Daniel. 1999. A decision-based approach to rhetorical parsing. In Proceedings off the 37th Annual Meeting, pages 365–372, University of Maryland, June. Association for Computational Linguistics. find
  48. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313-330.
  49. McDonald, David. 1996. Internal and external evidence in the identification and semantic categorization of proper names. In Bran Boguraev and James Pustejovsky, editors, Corpus Processing for Lexical Acquisition. MIT Press, Cambridge, MA, pages 21-39. find
  50. Mikheev, Andrei, Marc Moens, and Claire Grover. 1999. Named entity recognition without gazetteers. In Proceedings of EACL, pages 1-8, Bergen, Norway. EACL.
  51. Mitkov, Ruslan. 2000. Towards more comprehensive evaluation in anaphora resolution. In Proceedings of the 2nd International Conference on Language Resources and Evaluation, pages 1,309-1,314, Athens. find
  52. Paik, Woojin, Elizabeth D. Liddy, Edmund Yu, and Mary McKenna. 1996. Categorizing and standardizing proper nouns for efficient information retrieval. In Bran Boguraev and James Pustejovsky, editors, Corpus Processing for Lexical Acquisition. MIT Press, Cambridge, MA, pages 61-73. find
  53. Palmer, David D. and David S. Day. 1997. A statistical profile of the named entity task. find
  54. In Proceedings of the 5th Conference on Applied Natural Language Processing, pages 190-193, Washington, DC, March. Association for Computational Linguistics. find
  55. Poesio, Massimo. 1993. A situation-theoretic formalization of definite description interpretation in plan elaboration dialogues. In Peter Aczel, David Israel, Yasuhiro Katagiri, and Stanley Peters, editors, Situation Theory and its Applications, Volume 3. CSLI, Stanford, chapter 12, pages 339-374. find
  56. Poesio, Massimo, Sabine Schulte im Walde, and Chris Brew. 1998. Lexical clustering and definite description interpretation. In Proceedings of the AAAI Spring Symposium on Learning for Discourse, pages 82-89, Stanford, CA, March. AAAI. find
  57. Poesio, Massimo and Renata Vieira. 1998. A corpus-based investigation of definite description use. Computational Linguistics, 24(2):183-216.
  58. Poesio, Massimo, Renata Vieira, and Simone Teufel. 1997. Resolving bridging references in unrestricted text. In R. Mitkov, editor, Proceedings of the ACL Workshop on Operational Factors in Robust Anaphora Resolution, pages 1-6, Madrid.
  59. Also available as HCRC Research Paper HCRC/RP-87, University of Edinburgh. find
  60. Postal, Paul M. 1969. Anaphoric islands. In R. I. Binnick et al., editor, Papers~om the Fifth Regional Meeting of the Chicago Linguistic Society, pages 205-235. find
  61. Prince, Ellen F. 1981. Toward a taxonomy of given-new information. In Peter Cole, editor, Radical Pragmatics. Academic Press, New York, pages 223-256. find
  62. Prince, Ellen F. 1992. The ZPG letter: Subjects, definiteness, and information status. In S. Thompson and W. Mann, editors, Discourse Description: Diverse Analyses of a Fund-Raising Text. John Benjamins, pages 295-325. find
  63. Quinlan, J. Ross. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, CA.
  64. Quirk, Randolph, Sydney Greenbaum, Geoffrey Leech, and Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, London. find
  65. Reichman, Rachel. 1985. Getting Computers to Talk Like You and Me. MIT Press, Cambridge, MA. find
  66. Richmond, Kevin, Andrew Smith, and Einat Amitay. 1997. Detecting subject boundaries within text: A language-independent statistical approach. In Proceedings of The Second Conference on Empirical Methods in Natural Language Processing (EMNLP-2), pages 47-54, Brown University. find
  67. Russell, Bertrand. 1905. On denoting. Mind, 14:479-493. Reprinted in Logic and Knowledge, R. C. Marsh, editor, George Allen and Unwin, London. find
  68. Sidner, Candace L. 1979. Towards a computational theory of definite anaphora comprehension in English discourse. Ph.D. thesis, MIT. find
  69. Siegel, Sydney and N. John Castellan. 1988. find
  70. Nonparametric statistics for the Behavioral Sciences. 2nd edition. McGraw-Hill. find
  71. Strand, Kjetil. 1996. A taxonomy of linking relations. Manuscript. A preliminary version presented at the Workshop on Indirect Anaphora, Lancaster University, 1996. find
  72. Sundheim, Beth M. 1995. Overview of the results of the MUC-6 evaluation. In Proceedings of the Sixth Message Understanding Conference (MUC-6), pages 13-31, Columbia, MD, November 6-8. find
  73. Suri, Linda Z. and Kathleen 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
  74. Tetreault, Joel R. 1999. Analysis of syntax-based pronoun resolution methods. In Proceedings of the 37th Annual Meeting, pages 602-605, University of Maryland, June. Association for Computational Linguistics.
  75. Vieira, Renata. 1998. Definite Description Resolution in Unrestricted Texts. Ph.D. thesis, University of Edinburgh, Centre for Cognitive Science, February. find
  76. Vieira, Renata and Massimo Poesio. 1996. Processing definite descriptions in corpora. Presented at the Discourse Anaphora and Resolution Colloquium (DAARC), Lancaster University, Lancaster, UK. Also available as Research Paper HCRC/RP-86, University of Edinburgh, Human Communication Research Centre. find
  77. Vieira, Renata and Simone Teufel. 1997. Towards resolution of bridging descriptions. In Proceedings of the 35th Joint Meeting of the Association for Computational Linguistics, pages 522-524, Madrid.
  78. Vilain, Marc, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proc. of the Sixth Message Understanding Conference, pages 45-52.
  79. Wacholder, Nina and Yael. Ravin. 1997. Disambiguation of proper names in text. find
  80. In Proceedings of the 5th Conference on Applied Natural Language Processing, pages 202-208, Washington, DC, March. Association for Computational Linguistics. find
  81. Ward, Gregory, Richard Sproat, and Gail McKoon. 1991. A pragmatic analysis of so-called anaphoric islands. Language, 67:439-474. find
  82. Webber, Bonnie L. 1979. A Formal Approach to Discourse Anaphora. Garland, New York. find
  83. Wilks, Yorick A. 1975. A preferential pattern-matching semantics for natural language. Artificial Intelligence, 6:53-74. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/vieira-2000-empirically-based-system-processing-definite/