Event Graph Schema Induction with Path Language Modeling

Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers, Clare Voss
Contact: manling2@illinois.edu, hengji@illinois.edu



Figure 1: The framework of event graph schema induction. Given a news article, we construct an instance graph for every two event instances from information extraction (IE) results. In this example, instance graph (a) tells the story about Russia deploying troops to attack Ukraine using tanks from Russia; instance graph (b) is about Ukrainian protesters hit police using stones that are being carried to Maidan Square. We learn a path language model to select salient and coherent paths between two event types and merge them into a graph schema. The graph schema between Attack and Transport is an example output containing the top 20% ranked paths.


About

Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story.

Event Graph Schema Induction Task

  • Input: Instance graphs contaning entities, relations, and events from input documents.
  • Output: A set of recurring graph schemas from instance graphs.
    • Figure 1 shows the example input and output of event graph schema induction.

Paper        Slides        Video        GitHub


Acknowledgement

This research is based upon work supported in part by U.S. DARPA KAIROS Program Nos. FA8750-19-2-1004, FA8750-19-2-0500 and FA8750-19-2-1003, U.S. DARPA AIDA Program No. FA8750-18-2-0014 and Air Force No. FA8650-17-C-7715. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of DARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.


References

Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers, Clare Voss. "Connecting the Dots: Event Graph Schema Induction with Path Language Modeling." In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 684-695. 2020.

@inproceedings{li2020connecting, title={Connecting the Dots: Event Graph Schema Induction with Path Language Modeling}, author={Li, Manling and Zeng, Qi and Lin, Ying and Cho, Kyunghyun and Ji, Heng and May, Jonathan and Chambers, Nathanael and Voss, Clare}, booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={684--695}, year={2020} }