Where the Event Lies: Predicting Event Occurrence in Textual Documents

ABSTRACT

Manually inspecting text in a document collection to assess whether an event occurs in it is a cumbersome task. Although a manual inspection can allow one to identify and discard false events, it becomes infeasible with increasing numbers of automatically detected events. In this paper, we present a system to automatize event validation, defined as the task of determining whether a given event occurs in a given document or corpus. In addition to supporting users seeking for information that corroborates a given event, event validation can also boost the precision of automatically detected event sets by discarding false events and preserving the true ones. The system allows to specify events, retrieves candidate web documents, and assesses whether events occur in them. The validation results are shown to the user, who can revise the decision of the system. The validation method relies on a supervised model to predict the occurrence of events in a non-annotated corpus. This system can also be used to build ground-truths for event corpora.

References

1. J. Allan, R. Papka, and V. Lavrenko. On-line new event detection and tracking. In SIGIR, 1998.
2. J. Araki and J. Callan. An annotation similarity model in passage ranking for historical fact validation. In SIGIR, 2014.
3. A. Ceroni and M. Fisichella. Towards an entity-based automatic event validation. In ECIR, 2014.
4. A. Ceroni, U. Gadiraju, and M. Fisichella. Improving event detection by automatically assessing validity of event occurrence in text. In CIKM, 2015.
5. A. Das Sarma, A. Jain, and C. Yu. Dynamic relationship and event discovery. In Proc. of WSDM '11, 2011.
6. Q. He, K. Chang, and E.-P. Lim. Analyzing feature trajectories for event detection. In Proc. of SIGIR '07, 2007.
7. E. Kuzey and G. Weikum. Evin: Building a knowledge base of events. In Proc. of WWW '14, 2014.
8. A. J. McMinn, Y. Moshfeghi, and J. M. Jose. Building a large-scale corpus for evaluating event detection on twitter. In CIKM, 2013.
9. A. J. McMinn, D. Tsvetkov, T. Yordanov, A. Patterson, R. Szk, J. A. Rodriguez Perez, and J. M. Jose. An interactive interface for visualizing events on twitter. In Proc. of SIGIR '14, 2014.
10. V. Milicic, G. Rizzo, J. L. Redondo Garcia, R. Troncy, and T. Steiner. Live topic generation from event streams. In WWW '13, 2013.
11. A. Mishra and K. Berberich. ExposÉ: Exploring past news for seminal events. In Proc. of WWW '15, 2015.
12. J. B. Vuurens, A. P. de Vries, R. Blanco, and P. Mika. Online news tracking for ad-hoc queries. In Proc. of SIGIR '15, 2015.

Index Terms

• Information systems

  • Information retrieval

    • Evaluation of retrieval results

      • Test collections

    • Retrieval tasks and goals

      • Information extraction