Elamur Research⌕
☰
home / papers / 2019 / Detecting Subevents using Discourse and Narrative Features

Detecting Subevents using Discourse and Narrative Features

Summary

The authors address the task of subevent detection, that is, constructing a hierarchy of events. The goal is to determine whether one event in a text is a component of another, broader one: whether it takes place in the same location and at the same time. For each pair of events in which the first precedes the second in the text, a supervised learning model chooses one of three classes: a parent→child relation (PC), a relation in the reverse direction (CP), or no relation (NoRel). The authors take features from earlier systems, substantially refine some of them, and add new discourse- and narrative-level features. Among the new features are RST rhetorical relations between elementary discourse units, a direct-speech indicator, shared secondary coreferent mentions, and the distance between events. The model is the first to be evaluated on both corpora with annotated event hierarchies, HiEve and Intelligence Community (IC). On both, it outperformed previous systems. Error analysis shows which factors make the task hardest. This work is useful for information extraction and for a deeper understanding of news texts.

Key points

  • Results: 0.74 BLANC F1 on the IC corpus (15 pp better than Araki et al., 2014) and 0.70 F1 on HiEve (5 pp better than Glavaš and Šnajder, 2014b). To make the comparison fair, the authors reimplemented both previous systems.
  • Features are divided into five groups: lexical, syntactic, semantic, argument, and discourse-narrative. The tools used are spaCy, SEMAFOR, AllenNLP SRL, FastText (wiki-news-300d-1M), VerbOcean, and WordNet, together with a mapping of frames onto the 33 ACE 2005 event types.
  • The IC corpus is not publicly available: the authors obtained a copy directly from Hovy et al.
  • Error breakdown: about 60% are false positives (the model takes an unrelated pair for a subevent), about 28% are the wrong PC/CP direction (mostly due to an incorrect event type), and about 12% are missed relations when the events are far apart (more than 9 sentences or more than 14 intervening events).
  • The main source of false positives is sentences that mix two different event hierarchies. The authors tested the model on a subset of IC with 58 articles without such sentences. There, F1 rose by 6 pp for the PC class and by 4.6 pp for CP. Hence the proposal to split complex sentences into simple ones beforehand.

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

17 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 16 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1471

@inproceedings{aldawsari2019detecting,
  title = {{Detecting Subevents using Discourse and Narrative Features}},
  author = {Aldawsari, Mohammed and Finlayson, Mark},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1471},
  url = {https://doi.org/10.18653/v1/p19-1471}
}

References

41 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jun Araki. 2018. Extraction of Event Structures from Text. Ph.D. thesis, Carnegie Mellon University. find
  2. Jun Araki, Zhengzhong Liu, Eduard H Hovy, and Teruko Mitamura. 2014. Detecting subevent structure for event coreference resolution. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC), pages 4553–4558, Lisbon, Portugal. find our card
  3. Cosmin Adrian Bejan and Sanda M Harabagiu. 2008. A linguistic resource for discovering event structures and resolving event coreference. In Proceedings of the 6th Language Resources and Evaluation Conference (LREC), pages 2881–2887, Marrakech, Morocco. find our card
  4. Parminder Bhatia, Yangfeng Ji, and Jacob Eisenstein. 2015. Better document-level sentiment analysis from RST discourse parsing. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2212–2218, Lisbon, Portugal. find our card
  5. Lynn Carlson and Daniel Marcu. 2001. Discourse tagging reference manual. ISI Technical Report ISI-TR-545. find
  6. Timothy Chklovski and Patrick Pantel. 2004. VerbOcean: Mining the web for fine-grained semantic verb relations. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 33–40, Barcelona, Spain. find
  7. Prafulla Kumar Choubey and Ruihong Huang. 2018. Improving event coreference resolution by modeling correlations between event coreference chains and document topic structures. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Volume I, pages 485–495, Melbour… find our card
  8. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12:2493–2537. find our card
  9. Dan Cristea, Nancy Ide, and Laurent Romary. 1998. Veins theory: A model of global discourse cohesion and coherence. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (ACL-ICCL), pages 281–285, Mon… find
  10. Dipanjan Das, Nathan Schneider, Desai Chen, and Noah A Smith. 2010. Probabilistic frame-semantic parsing. In Proceedings of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pages 948–956, Los Angeles,… find our card
  11. Marie-Catherine De Marneffe, Anna N Rafferty, and Christopher D Manning. 2008. Finding contradictions in text. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-08 HLT), pages 1039–1047, Columbus, OH. find
  12. Leon Derczynski and Robert Gaizauskas. 2010. USFD2: Annotating temporal expresions and tlinks for tempeval-2. In Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval’10), pages 337–340, Los Angeles, CA. find
  13. Radu Florian, John F Pitrelli, Salim Roukos, and Imed Zitouni. 2010. Improving mention detection robustness to noisy input. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 335–345, Cambridge, MA. find
  14. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. Allennlp: A deep semantic natural language processing platform. arXiv preprint arXiv:1803.07640. find our card
  15. Goran Glavaš and Jan Šnajder. 2014b. Constructing coherent event hierarchies from news stories. In Proceedings of the Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-9), pages 34–38, Doha, Qatar. find
  16. Goran Glavaš, Jan Šnajder, Parisa Kordjamshidi, and Marie-Francine Moens. 2014a. Hieve: A corpus for extracting event hierarchies from news stories. In Proceedings of 9th Language Resources and Evaluation Conference (LREC), pages 3678–3683. find
  17. Aria D Haghighi, Andrew Y Ng, and Christopher D Manning. 2005. Robust textual inference via graph matching. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 387–394, Vancouver, Canada. find
  18. Luheng He, Kenton Lee, Mike Lewis, and Luke Zettlemoyer. 2017. Deep semantic role labeling: What works and what’s next. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Volume I, pages 473–483, Vancouver, Canada. find our card
  19. Matthew Honnibal and Ines Montani. spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. https://github.com/ explosion/spaCy; Last accessed on May 31, 2019. ↗
  20. Eduard Hovy, Teruko Mitamura, Felisa Verdejo, Jun Araki, and Andrew Philpot. 2013. Events are not simple: Identity, non-identity, and quasi-identity. In Proceedings of the Workshop on Events: Definition, Detection, Coreference, and Representation, pages 21–28, Atlanta, Georgia. find
  21. Kevin Humphreys, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pages 75–81, Madrid, Spain. find our card
  22. Silja Huttunen, Roman Yangarber, and Ralph Grishman. 2002. Complexity of event structure in ie scenarios. In Proceedings of the 19th International Conference on Computational Linguistics (COL-ING), pages 1–7, Taipei, Taiwan. find
  23. Shafiq Joty, Giuseppe Carenini, and Raymond T Ng. 2015. Codra: A novel discriminative framework for rhetorical analysis. Computational Linguistics, 41(3):385–435. find our card
  24. Angeliki Lazaridou, Ivan Titov, and Caroline Sporleder. 2013. A Bayesian model for joint unsupervised induction of sentiment, aspect and discourse representations. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL), Volume I, pages 1630–1639, Sofia, Bulg… find
  25. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 188–197, Copenhagen, Denmark. find our card
  26. Dekang Lin. 1998. An information-theoretic definition of similarity. In Proceedings of the 15th International Conference on Machine Learning (ICML), pages 296–304, San Francisco, CA. find
  27. Shulin Liu, Yubo Chen, Shizhu He, Kang Liu, and Jun Zhao. 2016. Leveraging framenet to improve automatic event detection. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Volume I, pages 2134– 2143, Berlin, Germany. find our card
  28. 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
  29. Mstislav Maslennikov and Tat-Seng Chua. 2007. A multi-resolution framework for information extraction from free text. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL), pages 592–599, Prague, Czech Republic. find
  30. Tomas Mikolov, Edouard Grave, Piotr Bojanowski, and Armand Puhrsch, Christian andJoulin. 2018. Advances in pre-training distributed word representations. In Proceedings of the 11th Language Resources and Evaluation Conference (LREC), Miyazaki, Japan. find our card
  31. Srini Narayanan and Sanda Harabagiu. 2004. Question answering based on semantic structures. In Proceedings of the 20th International Conference on Computational Linguistics (COLING), pages 693– 701, Geneva, Switzerland. find
  32. Arne Neumann. 2015. discoursegraphs: A graph-based merging tool and converter for multilayer annotated corpora. In Proceedings of the 20th Nordic Conference of Computational Linguistics (NODAL-IDA 2015), pages 309–312, Vilnius, Lithuania. find
  33. Qiang Ning, Zhili Feng, and Dan Roth. 2017. A structured learning approach to temporal relation extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1027–1037, Copenhagen, Denmark. find
  34. Fabian Pedregosa, Gael Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Edouard Duchesnay. 2011. Scikit-learn:… find
  35. Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, and Bonnie Webber. 2005. The Penn Discourse TreeBank as a resource for natural language generation. In Proceedings of the Corpus Linguistics Workshop on Using Corpora for Natural Language Generation, pages 25–32, Birmingham, UK… find our card
  36. James Pustejovsky, José M Castano, Robert Ingria, Roser Sauri, Robert J Gaizauskas, Andrea Setzer, Graham Katz, and Dragomir R Radev. 2003. TimeML: Robust specification of event and temporal expressions in text. In Proceedings of the 2003 AAAI Spring Symposium on New Directions in Question Answerin… find
  37. Marta Recasens and Eduard Hovy. 2011. Blanc: Implementing the rand index for coreference evaluation. Natural Language Engineering, 17(4):485– 510. find
  38. Swapna Somasundaran. 2010. Discourse-level relations for Opinion Analysis. Ph.D. thesis, University of Pittsburgh. find
  39. Naushad UzZaman and James Allen. 2011. Temporal evaluation. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT), pages 351–356, Portland, OR. find
  40. Suzan Verberne, LWJ Boves, NHJ Oostdijk, and PAJM Coppen. 2007. Evaluating discourse-based answer extraction for why-question answering. In Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pages 735–736, Amsterdam, The Ne… find
  41. Zhibiao Wu and Martha Palmer. 1994. Verbs semantics and lexical selection. In Proceedings of the 32nd Annual Meeting on Association for Computational Linguistics (ACL), pages 133–138, Las Cruces, NM. find

↑ back to top

This page in Markdown →