The premise of this project is that crime drama exemplified in television programs such as CSI: Crime Scene Investigation is an ideal testbed for approximating real-world natural language understanding and the complex inferences associated with it.
We propose to treat crime drama as a new inference task, capitalizing on the fact that each episode poses the same basic question (i.e., who committed the crime) and naturally provides the answer when the perpetrator is revealed.
Click here for the following paper.
@article{frermann-17,
author = "L. Frermann and S. B. Cohen and M. Lapata",
title = "Whodunnit? Crime Drama as a Case for Natural Language Understanding",
journal = "Transactions of the Association for Computational Linguistics",
year = "2017"
}
The dataset can be found on github.com.
Our work was in the news:
BBC,
New Scientist,
Scottish Legal,
The Register,
The Telegraph,
Daily Mail,
The Scotsman,
Scottish Daily Mail,
Digital Trends,
Geeks Squawk.