Elamur Research⌕
☰
home / papers / 2004 / Acquiring the Meaning of Discourse Markers

Acquiring the Meaning of Discourse Markers

Summary

The paper investigates whether core semantic properties of English discourse markers can be learned automatically from corpus data. This matters because manual taxonomies are incomplete. For example, Knott lists about 350 markers but classifies only around 150. Hutchinson focuses on structural connectives, which behave like coordinating or subordinating conjunctions. Each marker is classified along three dimensions: polarity (positive vs. negative, i.e. contrast or concession), veridicality (whether both arguments are asserted true) and type (ADDITIVE, TEMPORAL or CAUSAL).

The data come from a database of sentences that were automatically drawn from two sources, the British National Corpus and the web. Each sentence was parsed with the Charniak parser and filtered with syntactic heuristics. Every marker is represented by features from the clauses it links: lexical co-occurrences (especially with other discourse markers) and linguistically motivated syntactic, semantic and discourse features. The paper compares 1NN and Naive Bayes classifiers and uses Weka to select informative features. Naive Bayes trained on co-occurrences with the most informative markers exceeded 90% accuracy on all three tasks. The paper argues this also supports treating TEMPORAL markers as a distinct class.

Key points

  • Database: sentences for 140 structural connectives.
    • A manual check of 500 sentences found about 12% noise.
    • Marker frequency ranged from 270 ("the instant") to 331,701 ("and"), with a median of 4,948.
  • Gold-standard labels: compiled from Knott (1996), Knott and Dale (1994) and Louwerse (2001). Contentious or ambiguous markers were left out.
  • Best results (Naive Bayes on selected marker co-occurrences):
    • Polarity: 90.7% vs. a 67.4% baseline.
    • Veridicality: 91.8% vs. 73.5%.
    • Type: 93.5% vs. 58.1%.
    • These correspond to error reductions of 71.5%, 69.1% and 84.5%.
  • Linguistic features alone performed much worse. Naive Bayes using these features peaked at roughly 72–80% accuracy. Simple co-occurrence features outperformed the more sophisticated ones.
  • Feature findings:
    • Verbs and adverbs were the most useful co-occurring parts of speech.
    • Negation correlated with NEG-POL main clauses and with CAUSAL subordinate clauses.
    • Second-person pronouns correlated with NON-VERIDICAL markers.

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

Cited by

8 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 6 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/1218955.1219042

@inproceedings{hutchinson2004acquiring,
  title = {{Acquiring the Meaning of Discourse Markers}},
  author = {Hutchinson, Ben},
  booktitle = {Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)},
  year = {2004},
  doi = {10.3115/1218955.1219042},
  url = {https://doi.org/10.3115/1218955.1219042}
}

References

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

  1. Nicholas Asher and Alex Lascarides. 2003. Logics of Conversation. Cambridge University Press. find
  2. Timothy Baldwin and Francis Bond. 2003. Learning the countability of English nouns from corpus data. In Proceedings of ACL 2003, pages 463–470. find
  3. Yves Bestgen, Liesbeth Degand, and Wilbert Spooren. 2003. On the use of automatic techniques to determine the semantics of connectives in large newspaper corpora: An exploratory study. In Proceedings of the MAD’03 workshop on Multidisciplinary Approaches to Discourse, October. find
  4. Eugene Charniak. 2000. A maximum-entropy-inspired parser. In Proceedings of the First Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-2000), Seattle, Washington, USA. find our card
  5. James R. Curran and M. Moens. 2002. Improvements in automatic thesaurus extraction. In Proceedings of the Workshop on Unsupervised Lexical Acquisition, pages 59–67, Philadelphia, PA, USA. find
  6. Barbara Di Eugenio, Johanna D. Moore, and Massimo Paolucci. 1997. Learning features that predict cue usage. In Proceedings of the 35th Conference of the Association for Computational Linguistics (ACL97), Madrid, Spain, July. ↗
  7. Katherine Forbes, Eleni Miltsakaki, Rashmi Prasad, Anoop Sarkar, Aravind Joshi, and Bonnie Webber. 2001. D-LTAG system—discourse parsing with a lexicalised tree adjoining grammar. In Proceedings of the ESSLI 2001 Workshop on Information Structure, Discourse Structure, and Discourse Semantics, Helsinki, Finland. find
  8. Brigitte Grote and Manfred Stede. 1998. Discourse marker choice in sentence planning. In Eduard Hovy, editor, Proceedings of the Ninth International Workshop on Natural Language Generation, pages 128– 137. Association for Computational Linguistics, New Brunswick, New Jersey. find
  9. M. Halliday and R. Hasan. 1976. Cohesion in English. Longman. find
  10. Ben Hutchinson. 2003. Automatic classification of discourse markers by their co-occurrences. In Proceedings of the ESSLLI 2003 workshop on Discourse Particles: Meaning and Implementation, Vienna, Austria. find
  11. Ben Hutchinson. 2004. Mining the web for discourse markers. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC 2004), Lisbon, Portugal. find
  12. Alistair Knott and Robert Dale. 1994. Using linguistic phenomena to motivate a set of coherence relations. Discourse Processes, 18(1):35–62. ↗
  13. Alistair Knott. 1996. A data-driven methodology for motivating a set of coherence relations. Ph.D. thesis, University of Edinburgh. find
  14. Mirella Lapata and Alex Lascarides. 2004. Inferring sentence-internal temporal relations. In In Proceedings of the Human Language Technology Conference and the North American Chapter of the Association for Computational Linguistics Annual Meeting, Boston, MA. find our card
  15. Alex Lascarides and Nicholas Asher. 1993. Temporal interpretation, discourse relations and common sense entailment. Linguistics and Philosophy, 16(5):437– 493. find
  16. Lillian Lee. 2001. On the effectiveness of the skew divergence for statistical language analysis. Artificial Intelligence and Statistics, pages 65–72. find
  17. Max M Louwerse. 2001. An analytic and cognitive parameterization of coherence relations. Cognitive Linguistics, 12(3):291–315. find
  18. Inderjeet Mani and George Wilson. 2000. Robust temporal processing of news. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL 2000), pages 69–76, New Brunswick, New Jersey. find
  19. Daniel Marcu and Abdessamad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-2002), Philadelphia, PA. find our card
  20. Daniel Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. The MIT Press. ↗
  21. Jim Martin. 1992. English Text: System and Structure. Benjamin, Amsterdam. ↗
  22. M. Moser and J. Moore. 1995. Using discourse analysis and automatic text generation to study discourse cue usage. In Proceedings of the AAAI 1995 Spring Symposium on Empirical Methods in Discourse Interpretation and Generation, pages 92–98. find
  23. Jon Oberlander and Alistair Knott. 1995. Issues in cue phrase implicature. In Proceedings of the AAAI Spring Symposium on Empirical Methods in Discourse Interpretation and Generation. find
  24. Ted J. M. Sanders, W. P. M. Spooren, and L. G. M. Noordman. 1992. Towards a taxonomy of coherence relations. Discourse Processes, 15:1–35. find
  25. Suzanne Stevenson and Paola Merlo. 1999. Automatic verb classification using distributions of grammatical features. In Proceedings of the 9th Conference of the European Chapter of the ACL, pages 45–52, Bergen, Norway. find
  26. Bonnie Webber, Matthew Stone, Aravind Joshi, and Alistair Knott. 2003. Anaphora and discourse structure. Computational Linguistics, 29(4):545–588. ↗ our card
  27. Ian H. Witten and Eibe Frank. 2000. Data Mining: Practical machine learning tools with Java implementations. Morgan Kaufmann, San Francisco. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hutchinson-2004-acquiring-meaning-discourse-markers/