Capsule

View the Project on GitHub ajbc/capsule

Detecting and Characterizing Events

Significant events are characterized by interactions between entities (such as countries, organizations, or individuals) that deviate from typical interaction patterns. Analysts, including historians, political scientists, and journalists, commonly read large quantities of text to construct an accurate picture of when and where an event happened, who was involved, and in what ways. We present the Capsule model for analyzing documents to detect and characterize events of potential significance. Specifically, we develop a model based on topic modeling that distinguishes between topics that describe "business as usual" and topics that deviate from these patterns.

A demostration of the model can be found here.

Publications

Detecting and Characterizing Events. EMNLP, 2016.

@inproceedings{Chaney2016,
    author = {Chaney, Allison J.B. and Wallach, Hanna and Connelly, Matthew and Blei, David M.},
    title = {Detecting and Characterizing Events},
    booktitle = {EMNLP},
    year = {2016},
}

For a full list of written materials related to this work, please visit the doc directory in the repo.