Elamur Research⌕
☰
home / papers / 2015 / Fast Rhetorical Structure Theory Discourse Parsing

Fast Rhetorical Structure Theory Discourse Parsing

Summary

Research on RST discourse parsing has mostly chased accuracy through new features and learning algorithms. Speed, robustness and usable implementations got less attention, and few systems were released. Heilman and Sagae address this with an open-source Python pipeline that segments text into elementary discourse units (EDUs) and then builds RST trees. They train and evaluate it on the RST Discourse Treebank, using syntax from a ZPar model retrained on Penn Treebank WSJ texts that do not overlap with the treebank.

  • Segmenter: a CRF tagger that reimplements an earlier baseline and uses lexical, POS and parse-tree features.
  • Parser: a greedy arc-standard shift-reduce parser. An ℓ1-regularized logistic regression classifier chooses each action from stack, queue, syntactic and positional features.

Accuracy comes somewhat below the best published systems. In exchange, the parser averages under half a second per document, roughly ten times faster than a recent competitor. This makes RST analysis practical in applied settings such as essay or news processing.

Key points

  • Data: the RST Discourse Treebank has 347 training and 38 test documents. About 40 training documents were held out for tuning. Relations are collapsed to 18 labels and trees are binarized.
  • Segmentation: the CRF++ model with ℓ2 regularization reaches 86.7 F1 on EDU-start tags (P 90.2, R 83.5). This is below the 90.7 of the reimplemented Xuan Bach et al. (2012) baseline and well under human agreement of 98.3.
  • Parsing: with gold segmentation, test-set F1 is 83.5 for span, 68.1 for nuclearity and 55.1 for relation. Human agreement is 88.7, 77.7 and 65.8. The best compared relation score is 61.8, from Ji and Eisenstein (2014).
  • Gold vs. automatic syntax: on the development set, gold Penn Treebank trees improve results by about 1–2 F1 points.
  • Speed and availability: parsing takes 0.40 s per test document on average (maximum 1.85 s) on a 2013 MacBook Pro. Feng and Hirst (2014) report 10.71 s on different hardware. The code is public at github.com/EducationalTestingService/discourse-parsing.

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 · Treebanks

Cited by

24 papers of our library cite it (of the 140673 whose bibliographies we read); 10 of them have a page here, 14 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.1505.02425 · arXiv 1505.02425

@misc{heilman2015fast,
  title = {{Fast Rhetorical Structure Theory Discourse Parsing}},
  author = {Heilman, Michael and Sagae, Kenji},
  year = {2015},
  doi = {10.48550/arxiv.1505.02425},
  eprint = {1505.02425},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1505.02425}
}

References

22 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurowski. 2001. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In Proceedings of the Second SIGdial Workshop on Discourse and Dialogue - Volume 16, SIGDIAL ’01, pages 1–10, Stroudsburg, PA, USA. Association for Computational Linguistics. ↗ our card
  2. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurowski, 2002. RST Discourse Treebank LDC2002T07. Philadelphia. find
  3. Eugene Charniak. 2000. A maximum-entropy-inspired parser. 1st Meeting of the North American Chapter of the Association for Computational Linguistics. find our card
  4. Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post-editing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 511–521, Baltimore, Maryland, June. Association for Computational Linguistics. find our card
  5. Hugo Hernault, Danushka Bollegala, and Mitsuru Ishizuka. 2010. A sequential model for discourse segmentation. In Proceedings of the 11th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing’10, pages 315–326, Berlin, Heidelberg. Springer-Verlag. find
  6. Yangfeng Ji and Jacob Eisenstein. 2014. Representation learning for text-level discourse parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13–24, Baltimore, Maryland, June. Association for Computational Linguistics. find our card
  7. Shafiq Joty and Alessandro Moschitti. 2014. Discriminative reranking of discourse parses using tree kernels. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2049–2060, Doha, Qatar, October. Association for Computational Linguistics. find our card
  8. Shafiq Joty, Giuseppe Carenini, and Raymond Ng. 2012. A novel discriminative framework for sentence-level discourse analysis. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 904–915, Jeju Island, Korea, July. Association for Computational Linguistics. find
  9. Shafiq Joty, Giuseppe Carenini, Raymond Ng, and Yashar Mehdad. 2013. Combining intra- and multi-sentential rhetorical parsing for document-level discourse analysis. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 486–496, Sofia, Bulgaria, August. Association for Computational Linguistics. find
  10. Dan Klein and Christopher D. Manning. 2003a. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 423–430, Sapporo, Japan, July. Association for Computational Linguistics. find our card
  11. Dan Klein and Christopher D Manning. 2003b. Fast exact inference with a factored model for natural language parsing. In S. Becker, S. Thrun, and K. Obermayer, editors, Advances in Neural Information Processing Systems 15, pages 3–10. MIT Press. find
  12. John Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the 18th International Conference on Machine Learning 2001 (ICML 2001), pages 282– 289. find
  13. Jiwei Li, Rumeng Li, and Eduard Hovy. 2014a. Recursive deep models for discourse parsing. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2061– 2069, Doha, Qatar, October. Association for Computational Linguistics. find our card
  14. Sujian Li, Liang Wang, Ziqiang Cao, and Wenjie Li. 2014b. Text-level discourse dependency parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25–35, Baltimore, Maryland, June. Association for Computational Linguistics. ↗
  15. Daniel Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press. ↗
  16. 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. ↗ our card
  17. J. Hall J. Nilsson A. Chanev G. Eryigit S. Kbler S. Marinov Nivre, J. and E. Marsi. 2007. Maltparser: A language-independent system for data-driven dependency parsing. 13(2):95–135. ↗
  18. Kenji Sagae and Alon Lavie. 2005. A classifier-based parser with linear run-time complexity. In Proceedings of the Ninth International Workshop on Parsing Technology, pages 125–132, Vancouver, British Columbia, October. Association for Computational Linguistics. find our card
  19. Kenji Sagae. 2009. Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing. In Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09), pages 81–84, Paris, France, October. Association for Computational Linguistics. find
  20. Radu Soricut and Daniel Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1, NAACL ’03, pages 149–156, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  21. Ngo Xuan Bach, Nguyen Le Minh, and Akira Shimazu. 2012. A reranking model for discourse segmentation using subtree features. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 160–168, Seoul, South Korea, July. Association for Computational Linguistics. find
  22. Yue Zhang and Stephen Clark. 2011. Syntactic processing using the generalized perceptron and beam search. Computational Linguistics, 37(1). ↗

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/heilman-2015-fast-rhetorical-structure-theory-discourse/