This is the companion site for the paper:
Identifying civilians killed by police with distantly supervised entity-event extraction.
Katherine A. Keith,
Forthcoming, Proceedings of EMNLP 2017. [pdf]
We propose a new, socially-impactful task for natural language processing: from a news corpus, extract names of persons who have been killed by police. We present a newly collected police fatality corpus, which we release publicly, and present a model to solve this problem that uses EM-based distant supervision with logistic regression and convolutional neural network classifiers. Our model out- performs two off-the-shelf event extrac- tor systems, and we confirmed it suggests candidate victim names faster than one of the major manually-collected police fatality databases.
Code and Datasets
We release two versions of the data. If you use them in research, please cite the paper.
Supporting code and evaluation scripts are made available here