This directory contains two evaluation sets used in:

Ellie Pavlick and Marius Pasca. Identifying 1950s American Jazz Musicians: Fine-Grained Isa Extraction via Modifier Composition. ACL 2017.

@InProceedings{PP17,
  author    = {Ellie Pavlick and Marius Pa\c{s}ca},
  title     = {Identifying 1950s {A}merican Jazz Musicians: Fine-Grained {IsA} Extraction via Modifier Composition},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL-17)},
  year      = {2017},
  address   = {Vancouver, Canada},
}

The files in the directory are:

- wikiSample-uniform-classAndInstance.txt (referred to as UniformSet in paper): class labels chosen uniformly at random;
- wikiSample-weighted-classAndInstance.txt (referred to as WeightedSet in paper): class labels chosen proportionally to the frequency of the head.
