Elamur Research
☰
home / papers / 2000 / The rhetorical parsing of unrestricted texts: a surface-based approach

The rhetorical parsing of unrestricted texts: a surface-based approach

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/J00-3005.pdf

Summary

This paper asks how far one can get in automatically building rhetorical structure trees (RS-trees, following Mann and Thompson's 1988 RST conventions) for arbitrary real-world text without deep semantic or syntactic analysis. Marcu argues that earlier approaches fell into two camps. Formal, logic-heavy theories could not cope with naturally occurring text. Descriptive theories were too loosely specified to implement. His proposal sits between them. It combines shallow surface cues (punctuation, cue phrases/connectives, and lexical cohesion) with a first-order formal model of what counts as a valid RS-tree. The parser works in three stages:

  • it decides which connectives have a discourse role and splits sentences into clause-like elementary units;
  • it proposes candidate rhetorical relations between units and spans;
  • it outputs only well-formed trees.

The cue-phrase knowledge comes from a corpus study. Evaluation has two parts. Intrinsically, automatic trees are compared with hand-built ones. Extrinsically, the trees are used to drive a summarizer. Despite imperfect trees, the summarizer selects important text units at close to human performance. This shows that even noisy discourse structure is practically useful.

Key points

  • The parser relies only on surface-form processing: cue phrases, orthography and cohesion. It uses clause-like units as tree leaves, unlike Sumita et al. and Kurohashi and Nagao, whose systems need full parses and treat sentences as units.
  • Elementary unit boundaries are found with roughly 80% accuracy using these lean resources alone.
  • Because the formal constraints guarantee valid RS-trees, the parser avoids producing invalid structures, a problem the author attributes to Sumita et al.'s system.
  • The approach has clear weaknesses. It struggles with intentional relations such as EVIDENCE. It also has trouble telling apart ELABORATION, BACKGROUND, SEQUENCE and JOINT.
  • The summarizer exploits only the nucleus/satellite distinction and tree hierarchy. The author suggests possible further uses in IR, MT, coreference and QA.

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 · Natural language processing

Topics: Discourse analysis

Cited by

64 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 60 not yet.

Cite

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

@article{marcu2000rhetorical,
  title = {{The rhetorical parsing of unrestricted texts: a surface-based approach}},
  author = {Marcu, Daniel},
  journal = {Computational Linguistics},
  year = {2000},
  doi = {10.1162/089120100561755},
  url = {https://doi.org/10.1162/089120100561755}
}

References

72 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Asher, Nicholas. 1993. Reference to Abstract Objects in Discourse. Kluwer Academic Publishers, Dordrecht. find
  2. Asher, Nicholas and Alex Lascarides. 1994. Intentions and information in discourse. In Proceedings of the 32nd Annual Meeting, pages 34-41, New Mexico State University, Las Cruces, NM, June. Association for Computational Linguistics. find
  3. Bestgen, Yves and Jean Costermans. 1997. Temporal markers of narrative structure: Studies in production. In Jean Costermans and Michel Fayol, editors, Processing Interclausal Relationships. Studies in the Production and Comprehension of Text. Lawrence Erlbaum Associates, Hillsdale, NJ, pages 201-218. find
  4. Briscoe, Ted. 1996. The syntax and semantics of punctuation and its use in interpretation. In Proceedings of the Association for Computational Linguistics Workshop on Punctuation, pages 1-7, Santa Cruz, CA, June. find
  5. Bruder, Gail A. and Janice M. Wiebe. 1990. Psychological test of an algorithm for recognizing subjectivity in narrative text. In Proceedings of the Twelfth Annual Conference on the Cognitive Science Society, pages 947-953, Cambridge, MA, July. find
  6. Corston-Oliver, Simon H. 1998. Beyond string matching and cue phrases: Improving efficiency and coverage in discourse analysis. In Working Notes of the AAAI Spring Symposium on Intelligent Text Summarization, pages 9-15, Stanford, March. find
  7. Corston-Oliver, Simon H. and William B. Dolan. 1999. Less is more: Eliminating index terms from subordinate clauses. In Proceedings of the 37th Annual Meeting, pages 349-356, University of Maryland, June. Association for Computational Linguistics. find
  8. Cristea, Dan, Nancy Ide, Daniel Marcu, and Valentin Tablan. 1999. Discourse structure and coreference: An empirical study. In Proceedings of the ACL'99 Workshop on the Relationship Between Discourse~Dialogue Structure and Reference, pages 46-53, University of Maryland, June. find
  9. Cristea, Dan and Bonnie L. Webber. 1997. Expectations in incremental discourse processing. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics (ACL/EACL-97), pages 88-95, Madrid, Spain, July. find
  10. Crystal, David. 1991. A Dictionary of Linguistics and Phonetics. Third edition. Basil Blackwell, Oxford. find
  11. Cumming, Carmen and Catherine McKercher. 1994. The Canadian Reporter: News Writing and Reporting. Harcourt Brace. find
  12. Di Eugenio, Barbara, Johanna D. Moore, and Massimo Paolucci. 1997. Learning features that predict cue usage. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics (ACL/EACL-97), pages 80-87, Madrid, Spain, July. find
  13. Fraser, Bruce. 1996. Pragmatic markers. Pragmatics, 6(2):167-190. find
  14. Gardent, Claire. 1997. Discourse TAG. Technical Report CLAUS-Report Nr. 89, Universit/it des Saarlandes, Saarbr~icken, April. find
  15. Grosz, Barbara J., Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203-226. find our card
  16. Grosz, Barbara J. and Candace L. Sidner. 1986. Attention, intentions, and the structure of discourse. Computational Linguistics, 12(3):175-204. find our card
  17. Grote, Brigitte, Nils Lenke, and Manfred Stede. 1997. Ma(r)king concessions in English and German. Discourse Processes, 24:87-117. find our card
  18. Halliday, Michael A. K. and Ruqaiya Hasan. 1976. Cohesion in English. Longman. find
  19. Harabagiu, Sanda and Steven Maiorano. 1999. Knowledge-lean coreference resolution and its relation to textual cohesion and coreference. In Proceedings of the ACL'99 Workshop on Discourse/Dialogue Structure and Reference, pages 29-38, University of Maryland, June. find
  20. Harabagiu, Sanda M. and Dan I. Moldovan. 1996. Textnet--A text-based intelligent system. In Working Notes of the AAAI Fall Symposium on Knowledge Representation Systems Based on Natural Language, pages 32-43, Cambridge, MA. find
  21. Hearst, Marti A. 1997. TextTiling: Segmenting text into multi-paragraph subtopic passages. Computational Linguistics, 23(1):33-64. find
  22. Heurley, Laurent. 1997. Processing units in written texts: Paragraphs or information blocks. In Jean Costermans and Michel Fayol, editors, Processing Interclausal Relationships. Studies in the Production and Comprehension of Text. Lawrence Erlbaum Associates, pages 179-200. find
  23. Hirschberg, Julia and Diane Litman. 1993. Empirical studies on the disambiguation of cue phrases. Computational Linguistics, 19(3):501-530. find
  24. Hirschman, Lynette, Marc Light, Eric Breck, and John D. Burger. 1999. Deep read: A reading comprehension system. In Proceedings of the 37th Annual Meeting, pages 325-332, University of Maryland, June. Association for Computational Linguistics. find
  25. Hobbs, Jerry R. 1990. Literature and Cognition. CSLI Lecture Notes Number 21. find
  26. Hobbs, Jerry R., Mark Stickel, Douglas Appelt, and Paul Martin. 1993. Interpretation as abduction. Artificial Intelligence, 63:69-142. find
  27. Hoey, Michael. 1991. Patterns of Lexis in Text. Oxford University Press. find
  28. Jing, Hongyan, Regina Barzilay, Kathleen McKeown, and Michael Elhadad. 1998. Summarization evaluation methods: Experiments and analysis. In Proceedings of the AAAI-98 Spring Symposium on Intelligent Text Summarization, pages 60-68, Stanford, March. find
  29. Kameyama, Megumi. 1994. Indefeasible semantics and defeasible pragmatics. Technical Note 544, SRI International. A shorter version to appear in Kanazawa Makoto, Christopher Pinon, and Henriette de Swart, editors, Quantifiers, Deduction, and Context. CSLI, Stanford. find
  30. Kamp, Hans. 1981. A theory of truth and semantic interpretation. In J. A. G. Groenendijk, T. M. V. Janssen, and M. B. J. Stokhof, editors, Formal Methods in the Study of Language, Mathematical Centre Tracts 135. Mathematisch Centrum, Amsterdam, pages 277-322. find
  31. Kamp, Hans and Uwe Reyle. 1993. From Discourse to Logic: Introduction to ModelTheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory. Kluwer Academic Publishers, London, Boston, Dordrecht. Studies in Linguistics and Philosophy, Volume 42. find
  32. Kintsch, Walter. 1977. On comprehending stories. In Marcel Just and Patricia Carpenter, editors, Cognitive Processes in Comprehension. Lawrence Erlbaum Associates, Hillsdale, NJ. find
  33. Knott, Alistair. 1995. A Data-Driven Methodology for Motivating a Set of Coherence Relations. Ph.D. thesis, University of Edinburgh. find
  34. Kurohashi, Sadao and Makoto Nagao. 1994. Automatic detection of discourse structure by checking surface information in sentences. In Proceedings of the 15th International Conference on Computational Linguistics (COLING-94), volume 2, pages 1,123-1,127, Kyoto, Japan, August. find
  35. Lascarides, Alex and Nicholas Ashen 1993. Temporal interpretation, discourse relations, and common sense entailment. Linguistics and Philosophy, 16(5):437-493. find
  36. Litman, Diane J. 1996. Cue phrase classification using machine learning. Journal of Artificial Intelligence Research, 5:53-94. find
  37. Mann, William C. and Sandra A. Thompson. 1988. Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243-281. find our card
  38. Marcu, Daniel. 1996. Building up rhetorical structure trees. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), volume 2, pages 1,069-1,074, Portland, OR, August. find
  39. Marcu, Daniel. 1997a. The rhetorical parsing of natural language texts. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics (ACL-97), pages 96--103, Madrid, Spain, July. find
  40. Marcu, Daniel. 1997b. The Rhetorical Parsing, Summarization, and Generation of Natural Language Texts. Ph.D. thesis, Department of Computer Science, University of Toronto, December. find
  41. Marcu, Daniel. 1999a. A decision-based approach to rhetorical parsing. In Proceedings of the 37th Annual Meeting, pages 365-372, University of Maryland, June. Association for Computational Linguistics. find
  42. Marcu, Daniel. 1999b. Discourse trees are good indicators of importance in text. In Inderjeet Mani and Mark Maybury, editors, Advances in Automatic Text Summarization. MIT Press, Cambridge, MA, pages 123-136. find
  43. Marcu, Daniel. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press, Cambridge, MA. To appear. find
  44. Marcu, Daniel, Lynn Carlson, and Maki Watanabe. 2000. The automatic translation of discourse structures. In Proceedings of the Language Technology Joint Conference ANLP-NAACL2000, Seattle, WA. find
  45. Martin, James R. 1992. English Text. System and Structure. John Benjamin Publishing Company, Philadelphia, Amsterdam. find
  46. Morris, Jane and Graeme Hirst. 1991. Lexical cohesion computed by thesaural relations as an indicator of the structure of text. Computational Linguistics, 17(1):21-48. find our card
  47. Moser, Megan and Johanna D. Moore. 1997. On the correlation of cues with discourse structure: Results from a corpus study. Forthcoming. find
  48. Nunberg, G. 1990. The Linguistics of Punctuation. CSLI Lecture Notes 18, Stanford. University of Chicago Press. find
  49. Palmer, David D. and Marti A. Hearst. 1997. Adaptive multilingual sentence boundary disambiguation. Computational Linguistics, 23(2):241-269. find
  50. Pascual, Elsa and Jacques Virbel. 1996. Semantic and layout properties of text punctuation. In Proceedings of the Association for Computational Linguistics Workshop on Punctuation, pages 41-48, Santa Cruz, CA, June. find
  51. Polanyi, Livia. 1988. A formal model of the structure of discourse. Journal of Pragmatics, 12:601-638. find
  52. Polanyi, Livia. 1996. The linguistic structure of discourse. Technical Report CSLI-96-200, Center for the Study of Language and Information. find
  53. Polanyi, Livia and Martin H. van den Berg. 1996. Discourse structure and discourse interpretation. In P. Dekker and M. Stokhof, editors, Proceedings of the Tenth Amsterdam Colloquium, pages 113-131. Department of Philosophy, University of Amsterdam. find
  54. Redeker, Gisela. 1990. Ideational and pragmatic markers of discourse structure. Journal of Pragmatics, 14:367-381. find
  55. Salton, Gerard and James Allan. 1995. Selective text utilization and text traversal. International Journal of Human-Computer Studies, 43:483-497. find
  56. Salton, Gerard, Amit Singhal, Chris Buckley, and Mandar Mitra. 1995. Automatic text decomposition using text segments and text themes. Technical Report TR-95-1555, Department of Computer Science, Cornell University. find
  57. Say, Bilge and Varol Akman. 1996. Information-based aspects of punctuation. In Proceedings of the Association for Computational Linguistics Workshop on Punctuation, pages 49-56, Santa Cruz, CA, June. find
  58. Schiffrin, Deborah. 1987. Discourse Markers. Cambridge University Press. find
  59. Schilder, Frank. 1997. Tree discourse grammar, or how to get attached a discourse. In Proceedings of the Second International Workshop on Computational Semantics (IWCS-II), pages 261-273, Tilburg, The Netherlands, January. find
  60. Schneuwly, Bernard. 1997. Textual organizers and text types: Ontogenetic aspects in writing. In Jean Costermans and Michel Fayol, editors, Processing Interclausal Relationships. Studies in the Production and Comprehension of Text. Lawrence Erlbaum Associates, Hillsdale, NJ, pages 245-263. find
  61. Segal, Erwin M. and Judith F. Duchan. 1997. Interclausal connectives as indicators of structuring in narrative. In Jean Costermans and Michel Fayol, editors, Processing Interclausal Relationships. Studies in the Production and Comprehension of Text. Lawrence Erlbaum Associates, Hillsdale, NJ, pages 95-119. find
  62. Segal, Erwin M., Judith F. Duchan, and Paula J. Scott. 1991. The role of interclausal connectives in narrative structuring: Evidence from adults' interpretations of simple stories. Discourse Processes, 14:27-54. find
  63. Shiuan, Peh Li and Christopher Ting Hian Ann. 1996. A divide-and-conquer strategy for parsing. In Proceedings of the Association for Computational Linguistics Workshop on Punctuation, pages 57-66, Santa Cruz, CA, June. find
  64. Siegel, Eric V. and Kathleen R. McKeown. 1994. Emergent linguistic rules from inducing decision trees: Disambiguating discourse clue words. In Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI-94), volume 1, pages 820-826, Seattle, WA. find
  65. Strube, Michael and Udo Hahn. 1999. Functional centering---Grounding referential coherence in information structure. Computational Linguistics, 25(3):309-344. find
  66. Sumita, K., K. Ono, T. Chino, T. Ukita, and S. Amano. 1992. A discourse structure analyzer for Japanese text. In Proceedings of the International Conference on Fifth Generation Computer Systems, volume 2, pages 1,133-1,140. find
  67. van den Berg, Martin H. 1996. Discourse grammar and dynamic logic. In P. Dekker and M. Stokhof, editors, Proceedings of the Tenth Amsterdam Colloquium, pages 93-112. Department of Philosophy, University of Amsterdam. find
  68. van Dijk, Teun A. 1972. Some Aspects of Text Grammars; A Study in Theoretical Linguistics and Poetics. Mouton, The Hague. find
  69. Webber, Bonnie, Alistair Knott, Matthew Stone, and Aravind Joshi. 1999. Discourse relations: A structural and presuppositional account using lexicalized TAG. In Proceedings of the 37th Annual Meeting, pages 41-48, University of Maryland, June. Association for Computational Linguistics. find
  70. Wiebe, Janice M. 1994. Tracking point of view in narrative. Computational Linguistics, 20(2):233-288. find
  71. Youmans, Gilbert. 1991. A new tool for discourse analysis: The vocabulary-management profile. Language, 67(4):763-789. find
  72. Zock, Michael. 1985. Le fil d'ariane ou les grammaires de texte comme guide dans l'organisation et l'expression de la pens~e en langue maternelle et/ou 6trang6re. Technical Report, Rapport pour l'Unesco, Juin. find