Elamur Research⌕
☰
home / papers / 2015 / PDTB Discourse Parsing as a Tagging Task: The Two Taggers Approach

PDTB Discourse Parsing as a Tagging Task: The Two Taggers Approach

Summary

The paper tackles end-to-end discourse parsing in the Penn Discourse Treebank (PDTB) framework. In this setting, a system receives raw text and must find both explicit and implicit relations along with their arguments. The previous end-to-end system, the Lin parser, used a four-stage pipeline in which errors carry forward. The authors instead recast the problem as two sequence-labelling problems. One tagger assigns each sentence the relation found inside it. The other assigns each pair of neighbouring sentences the relation linking them. Both are chain CRFs, and the features cover explicit and implicit cues. Some features are new variants: production angles, dense word-pair similarity and expanded shared words. Argument spans come from a few simple heuristics rather than a complex syntactic module. Relations are predicted at the second (type) level of the PDTB hierarchy. Under partial-match evaluation, the system reaches an F1 of 39.33 and outperforms the Lin parser. The results suggest that sequential context matters, especially for relations between sentences. The parser is simpler, easier to extend and publicly released, which lowers the barrier to experimenting with PDTB parsing.

Key points

  • In the PDTB, 92.9% of annotated relations either sit inside one sentence or link two adjacent sentences, and the Two Taggers approach covers both cases. Its main blind spots are rare multi-relation sentences and non-adjacent arguments, all of which are explicit.
  • The target labels are 16 level-2 types plus EntRel and NoRel, 18 in total. The authors argue that level-1 classes are too coarse for many applications. Most earlier work used the easier class level.
  • Discourse connectives are detected with the Pitler and Nenkova (2009) classifier, which scores above 95 F1.
  • The span heuristics are effective under partial match. For adjacent pairs, treating each whole sentence as an argument fails for only 0.002% of training relations.
  • The CRF taggers clearly beat non-sequential classifiers that use the same features, especially for adjacent sentence pairs.
  • For implicit relations, the estimated lower-bound F-measure is 28.32 (precision 28.02, recall 28.63), compared with 25.46 for the Lin parser's implicit component.

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 · Part-of-speech tagging

Cited by

11 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/w15-4612

@inproceedings{biran2015pdtb,
  title = {{PDTB Discourse Parsing as a Tagging Task: The Two Taggers Approach}},
  author = {Biran, Or and McKeown, Kathleen},
  booktitle = {Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  year = {2015},
  doi = {10.18653/v1/w15-4612},
  url = {https://doi.org/10.18653/v1/w15-4612}
}

References

27 references, 17 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. Studies in Natural Language Processing Series. Cambridge University Press. find
  2. 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, ACL 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 2: Short Papers, pages 69–73. The Associat… find our card
  3. 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 Computat… find our card
  4. David A. duVerle and Helmut Prendinger. 2009. A novel discourse parser based on support vector machine classification. 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 - Volum… find our card
  5. Christiane Fellbaum, editor. 1998. WordNet An Electronic Lexical Database. The MIT Press. find
  6. 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, pages 511–521, Baltimore, Maryland, June. Association for Computational Linguistics. find our card
  7. Sucheta Ghosh, Richard Johansson, Giuseppe Riccardi, and Sara Tonelli. 2011. Shallow discourse parsing with conditional random fields. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 1071–1079. find our card
  8. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1, ACL ’03, pages 423– 430, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  9. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, pages 282–289, San Francisco, CA, USA. Morgan Kaufm… find
  10. Huong LeThanh, Geetha Abeysinghe, and Christian Huyck. 2004. Generating discourse structures for written texts. In Proceedings of the 20th International Conference on Computational Linguistics, COLING ’04, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  11. Jessy Junyi Li and Ani Nenkova. 2014a. Addressing class imbalance for improved recognition of implicit discourse relations. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 142–150. Association for Computational Linguistics. find
  12. Jessy Junyi Li and Ani Nenkova. 2014b. Reducing sparsity improves the recognition of implicit discourse relations. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 199–207. Association for Computational Linguistics. find our card
  13. Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng. 2009. Recognizing implicit discourse relations in the penn discourse treebank. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 343–351. find our card
  14. Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A pdtb-styled end-to-end discourse parser. Natural Language Engineering, 20(2):151–184. find
  15. William C. Mann and Sandra A. Thompson. 1987. Rhetorical Structure Theory: A theory of text organization. Technical Report ISI/RS-87-190, ISI. find
  16. Daniel Marcu and Abdessamad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In ACL, pages 368–375. ACL. find our card
  17. Daniel Marcu. 1997. The rhetorical parsing, summarization, and generation of natural language texts. Technical report. find
  18. Mitchell P. Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of english: The penn treebank. Comput. Linguist., 19(2):313–330, June. find our card
  19. Andrew McCallum and Wei Li. 2003. Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003 - Volume 4, CONLL ’03, pages 188–191, Stroudsburg, PA, USA… find our card
  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. find our card
  21. Emily Pitler and Ani Nenkova. 2009. Using syntax to disambiguate explicit discourse connectives in text. In ACL/IJCNLP (Short Papers), pages 13–16. The Association for Computer Linguistics. find our card
  22. Emily Pitler, Annie Louis, and Ani Nenkova. 2009. Automatic sense prediction for implicit discourse relations in text. In ACL/IJCNLP, pages 683–691. The Association for Computer Linguistics. find our card
  23. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The penn discourse treebank 2.0. In In Proceedings of LREC. find our card
  24. Fei Sha and Fernando Pereira. 2003. Shallow parsing with conditional random fields. 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 134–141, Stroudsburg, PA, USA. Associatio… find
  25. 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, Stro… find our card
  26. Ben Wellner. 2009. Sequence Models and Ranking Methods for Discourse Parsing. Ph.D. thesis, Waltham, MA, USA. AAI3339383. find
  27. Zhi-Min Zhou, Yu Xu, Zheng-Yu Niu, Man Lan, Jian Su, and Chew Lim Tan. 2010. Predicting discourse connectives for implicit discourse relation recognition. In Proceedings of the 23rd International Conference on Computational Linguistics. find our card

↑ back to top

This page in Markdown →