About

This is the project page for the paper titled “Unsupervised Learning of Style-sensitive Word Vectors” at ACL2018.

Code

Our training script is available on here.
This repository contains code for learning style-sensitive word vectors and analyzing them.

Data

Our dataset is available on here.
It is the evaluation dataset for stylistic word similarity task, which we proposed.

Reference

If you need, we would appreciate citations to the following paper:

Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi and Kentaro Inui. Unsupervised Learning of Style-sensitive Word Vectors. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, July. 2018.

@InProceedings{akama2018stylevec,
  title={Unsupervised Learning of Style-sensitive Word Vectors},
  author={Reina Akama and Kento Watanabe and Sho Yokoi and Sosuke Kobayashi and Kentaro Inui},
  booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics},
  year={2018}
}