Translating Granularity of Event Slots into Features for Event Coreference Resolution.

Summary

The paper addresses cross-document event coreference resolution in news: deciding whether two event mentions denote the same real-world event. The authors argue that grain size matters. A large, long event involving many participants, such as a war, may be related to a small, brief incident without being identical to it. They propose a pairwise "sentence template" model. Each mention is described by five slots: action, time, location, human participant and non-human participant. The slots are filled only from the sentence containing the mention and are compared by a supervised classifier. Granularity features come from three sources:

event durations;
a new WordNet-based granularity ontology covering times, locations and human participants;
number cues (singular vs. plural) derived from NLTK POS tags.

Experiments on ECB+ were run without topic clustering, anaphora resolution or syntactic information. Adding granularity features raises precision, and overall scores are comparable to earlier results on ECB. The work matters because it shows that the semantic scale of events helps coreference, and because the ontology is released for research.

Key points

The granularity ontology has 15 semantic classes, manually assigned to 434 WordNet hypernyms that cover 11979 synsets. The classes split into nine time levels, four location levels and two human-participant levels.
The ontology classes follow meronymic relation types from Winston et al. (1987): Member-Collection, Portion-Mass and Place-Area.
Event action durations follow Gusev et al. (2011). Granularity and number indications are compared per slot using cosine similarity.
The data is ECB+. ECB itself could not be used because it lacks the entity-type annotation that the granularity estimates require.
For comparison, prior ECB results include Lee et al. (2012) at 55.9% CoNLL F, on a harder task that includes mention extraction, and Cybulska and Vossen (2013) at 69.8%, on an easier within-topic task.

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: Coreference resolution

Cited by

26 papers of our library cite it (of the 140673 whose bibliographies we read); 13 of them have a page here, 13 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/w15-0801

@inproceedings{cybulska2015translating,
  title = {{Translating Granularity of Event Slots into Features for Event Coreference Resolution.}},
  author = {Cybulska, Agata and Vossen, Piek},
  booktitle = {Proceedings of the 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation},
  year = {2015},
  doi = {10.3115/v1/w15-0801},
  url = {https://doi.org/10.3115/v1/w15-0801}
}

References

23 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). find our card
Cosmin Adrian Bejan and Sanda Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden. find our card
Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural Language Processing with Python. O’Reilly Media Inc., http://nltk.org/book. ↗
Agata Cybulska and Piek Vossen. 2013. Semantic relations between events and their time, locations and participants for event coreference resolution. In Proceedings of recent advances in natural language processing (RANLP-2013). find our card
Agata Cybulska and Piek Vossen. 2014a. Guidelines for ECB+ annotation of events and their coreference. Technical Report NWR-2014-1, VU University Amsterdam. find
Agata Cybulska and Piek Vossen. 2014b. Using a sledgehammer to crack a nut? Lexical diversity and event coreference resolution. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2014). find our card
Agata Cybulska and Piek Vossen. 2015. “Bag of events” approach to event coreference resolution. Supervised classification of event templates. In International Journal of Computational Linguistics and Applications (IJCLA). find
Andrey Gusev, Nathanael Chambers, Pranav Khaitan, Divye Khilnani, Steven Bethard, and Dan Jurafsky. 2011. Using query patterns to learn the duration of events. In Proceedings of the Ninth International Conference on Computational Semantics (IWCS11). find
Jerry R. Hobbs. 1985. Granularity. In Proceedings of the Ninth International Joint Conference on Artificial Intelligence. find
Blake Stephen Howald and Martha Abramson. 2012. The use of granularity in rhetorical prediction. In Proceedings of the First Joint Conference on Lexi-cal and Computational Semantics (*SEM). find
Kevin Humphreys, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In ANARESOLUTION ’97 Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts. find our card
Catharina Maria Keet. 2008. A formal theory of granularity. toward enhancing biological and applied life sciences information systems with granularity. In Ph.D. thesis, Faculty of Computer Science, Free University of Bozen-Balzano, Italy. find
LDC. 2005. ACE (Automatic Content Extraction) English Annotation Guidelines for Events ver. 5.4.3 2005.07.01. In Linguistic Data Consortium. find
Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP-CoNLL). find our card
Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP-2005). find our card
Inderjeet Mani. 1998. A theory of granularity and its application to problems of polysemy and underspecification of meaning. In In Principles of Knowledge Representation and Reasoning: Proceedings of the Sixth International Conference (KR-98). find
Rutu Mulkar-Mehta, Jerry R. Hobbs, and Eduard Hovy. 2011a. Applications and discovery of granularity structures in natural language discourse. In Proceedings of The Tenth International Symposium on Logical Formalizations of Commonsense Reasoning at the AAAI Spring Symposium, Palo Alto. find
Rutu Mulkar-Mehta, Jerry R. Hobbs, and Eduard Hovy. 2011b. Granularity in natural language discourse. In Proceedings of International Conference on Computational Semantics. find
Fabian Pedregosa, Gal 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 douard Duchesnay. 2011. Scikit-learn: Ma… find
Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 shared task: Modeling unrestricted coreference in ontonotes. In Proceedings of CoNLL 2011: Shared Task. find our card
Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the rand index for coreference evaluation. Natural Language Engineering, 17(4):485–510. find
Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model theoretic coreference scoring scheme. In Proceedings of MUC-6. find our card
Morton E. Winston, Roger Chaffin, and Douglas Herrmann. 1987. A taxonomy of part-whole relations. In Cognitive Science Volume 11, Issue 4, pages 417 - 444. find

↑ back to top

📄 Translating Granularity of Event Slots into Features for Event Coreference Resolution.