Font prediction dataset

This is a repository for the ACL 2020 paper: "Let Me Choose: From Verbal Context to Font Selection"

The proposed dataset includes 1,309 short text instances from Adobe Spark. The dataset is a collection of publicly available sample texts created by different designers. It covers a variety of topics found in posters, flyers, motivational quotes and advertisements.

Examples from our collected dataset, visualized through fonts with the highest annotation agreements.

Data Format

We are currently releasing annotated data in .csv files.

| # | text | F0 | F1 | F2 | F3 | F4 | F5 | F6 | F7 | F8 | F9 |

Font Mappings

F0: Source-sans-pro
F1: Blakely
F2: FF-ernestine-pro
F3: FF-market-web
F4: Bickham-script-pro-3
F5: Burbank-big
F6: Fresno
F7: Sneakers-script-narrow
F8: Felt-tip-roman
F9: Pauline

Citation

If you use the Font corpus in your publication, please cite this paper:

@inproceedings{shirani2020font,
  title={Let Me Choose: From Verbal Context to Font Selection},
  author={Shirani, Amirreza and Dernoncourt, Franck and Echevarria, Jose and Asente, Paul and Lipka, Nedim and Solorio, Thamar},
  booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year={2020}
}