Elamur Research⌕
☰
home / papers / 2014 / Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns

Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns

Summary

Most discourse relations in running text have no explicit connective, and recognizing their senses is a known weak spot of end-to-end discourse parsers. Earlier systems relied on word-pair features, which are sparse because many pairs seen in training never occur at test time. Rutherford and Xue address this by mapping every word to its Brown cluster and using all cross-argument cluster pairs as features. This yields a far smaller and denser feature space. They add a compact set of coreference-based features, such as counts of shared entities and whether subjects or main verbs coincide. Experiments use the Penn Discourse Treebank (PDTB) with one-vs-all binary classification for each top-level sense. All preprocessing comes from automatic tools rather than gold annotations. On every task, the system outperforms the baselines from Park and Cardie (2012) as well as those from Pitler et al. (2009). Feature analysis indicates that cluster pairs capture meaningful lexical patterns and that coreference behaviour differs systematically across relation types. This gives a stronger baseline for implicit relation classification.

Key points

  • Data and setup: PDTB top-level senses COMPARISON, CONTINGENCY, EXPANSION and TEMPORAL, plus an EXPANSION+ENTREL task. Sections 2–20 are used for training, 0–1 for development and 21–22 for testing. Preprocessing relies on Stanford CoreNLP, and classifiers come from MALLET and libSVM.

  • Brown clusters: the 3,200 clusters from MetaOptimize were induced on RCV1, which has about 63M tokens of Reuters newswire. The Cartesian product of Arg1 and Arg2 cluster IDs bounds the feature space at roughly 3200² instead of V².

  • F1 scores compared with Park and Cardie (2012):

    TaskThis paperPark and Cardie (2012)
    COMPARISON39.7031.32
    CONTINGENCY54.4249.82
    EXP+ENTREL80.4479.22
    TEMPORAL28.6926.57

  • Ablations:

    • Removing the cluster-pair features lowers COMPARISON F1 to 35.71, a relative drop of about 10%.
    • Removing the coreference features costs about 1% on TEMPORAL and CONTINGENCY.

  • Class imbalance and coreference findings:

    • Imbalance is handled by reweighting training samples per class rather than discarding data.
    • TEMPORAL pairs show the highest coreference rates, while CONTINGENCY has the lowest subject-coreference rate.
    • Code is available at github.com/attapol/brown_coref_implicit.

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 · Coreference resolution

Cited by

64 papers of our library cite it (of the 140673 whose bibliographies we read); 34 of them have a page here, 30 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/e14-1068

@inproceedings{rutherford2014discovering,
  title = {{Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns}},
  author = {Rutherford, Attapol and Xue, Nianwen},
  booktitle = {Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics},
  year = {2014},
  doi = {10.3115/v1/e14-1068},
  url = {https://doi.org/10.3115/v1/e14-1068}
}

References

33 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Or Biran and Kathleen McKeown. 2013. Aggregated word pair features for implicit discourse relation disambiguation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 69–73. The Association for Computational Linguistics. find our card
  2. Peter F Brown, Peter V deSouza, Robert L Mercer, Vincent J Della Pietra, and Jenifer C Lai. 1992. Class-based n -gram models of natural language. Computational Linguistics, 18(4):467–479, December. find
  3. Chih-Chung Chang and Chih-Jen Lin. 2011. LIB-SVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27. Software available at http://www.csie.ntu.edu.tw/˜cjlin/libsvm. ↗
  4. Marie-Catherine De Marneffe, Bill MacCartney, Christopher D Manning, et al. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of LREC, volume 6, pages 449–454. find our card
  5. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by gibbs sampling. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 363–370. Association for Computational Linguistic… find
  6. Nathalie Japkowicz. 2000. Learning from imbalanced data sets: a comparison of various strategies. In AAAI workshop on learning from imbalanced data sets, volume 68. find
  7. Michael Jordan and Andrew Ng. 2002. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. Advances in neural information processing systems, 14:841. find
  8. Dan Klein and Christopher D Manning. 2003. Accurate unlexicalized parsing. In the 41st Annual Meeting, pages 423–430, Morristown, NJ, USA. Association for Computational Linguistics. find our card
  9. Heeyoung Lee, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 28–… find our card
  10. Heeyoung Lee, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics. find our card
  11. Beth Levin. 1993. English verb classes and alternations: A preliminary investigation, volume 348. University of Chicago press Chicago. find
  12. Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2010. A PDTB-Styled End-to-End Discourse Parser. arXiv.org, November. find
  13. Nick Littlestone. 1988. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine learning, 2(4):285–318. find
  14. Annie Louis and Ani Nenkova. 2010. Creating local coherence: An empirical assessment. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 313–316. Association for Computational Linguistics. find
  15. Annie Louis, Aravind Joshi, Rashmi Prasad, and Ani Nenkova. 2010. Using entity features to classify implicit discourse relations. In Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 59–62. Association for Computational Linguistics. find our card
  16. William C Mann and Sandra A Thompson. 1988. Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243–281. find our card
  17. Daniel Marcu and Abdessamad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 368–375. Association for Computational Linguistics. find our card
  18. Mitchell P Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of english: The penn treebank. Computational linguistics, 19(2):313–330. find our card
  19. Andrew Kachites McCallum. 2002. Mallet: A machine learning for language toolkit. http://www.cs.umass.edu/ mccallum/mallet. ↗
  20. Joonsuk Park and Claire Cardie. 2012. Improving implicit discourse relation recognition through feature set optimization. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 108–112. Association for Computational Linguistics. find our card
  21. Gary Patterson and Andrew Kehler. 2013. Predicting the presence of discourse connectives. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. find our card
  22. Emily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee, and Aravind K Joshi. 2008. Easily identifiable discourse relations. Technical Reports (CIS), page 884. find our card
  23. Emily Pitler, Annie Louis, and Ani Nenkova. 2009. Automatic sense prediction for implicit discourse relations in text. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2-Volume… find our card
  24. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind K Joshi, and Bonnie L Webber. 2008. The penn discourse treebank 2.0. In LREC. Citeseer. find our card
  25. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP ’10, pages 492–501… find our card
  26. Alan Ritter, Sam Clark, Oren Etzioni, et al. 2011. Named entity recognition in tweets: an experimental study. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1524–1534. Association for Computational Linguistics. find
  27. Philip Stone, Dexter C Dunphy, Marshall S Smith, and DM Ogilvie. 1968. The general inquirer: A computer approach to content analysis. Journal of Regional Science, 8(1). find
  28. Kristina Toutanova and Christopher D Manning. 2000. Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual… find
  29. Kristina Toutanova, Dan Klein, Christopher D Manning, and Yoram Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume… find
  30. Joseph Turian, Lev Ratinov, and Yoshua Bengio. 2010. Word representations: a simple and general method for semi-supervised learning. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 384–394. Association for Computational Linguistics. find our card
  31. Xun Wang, Sujian Li, Jiwei Li, and Wenjie Li. 2012. Implicit discourse relation recognition by selecting typical training examples. In Proceedings of COL-ING 2012, pages 2757–2772, Mumbai, India, December. find our card
  32. The COLING 2012 Organizing Committee. find
  33. Ben Wellner, James Pustejovsky, Catherine Havasi, Anna Rumshisky, and Roser Sauri. 2009. Classification of discourse coherence relations: An exploratory study using multiple knowledge sources. In Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue, pages 117–125. Association for Comput… find

↑ back to top