@inproceedings{kann-monsalve-mercado-2021-coloring,
    title = "Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings",
    author = "Kann, Katharina  and
      Monsalve-Mercado, Mauro M.",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.eacl-main.230/",
    doi = "10.18653/v1/2021.eacl-main.230",
    pages = "2673--2685",
    abstract = "In contrast to their word- or sentence-level counterparts, character embeddings are still poorly understood. We aim at closing this gap with an in-depth study of English character embeddings. For this, we use resources from research on grapheme{--}color synesthesia {--} a neuropsychological phenomenon where letters are associated with colors {--}, which give us insight into which characters are similar for synesthetes and how characters are organized in color space. Comparing 10 different character embeddings, we ask: How similar are character embeddings to a synesthete`s perception of characters? And how similar are character embeddings extracted from different models? We find that LSTMs agree with humans more than transformers. Comparing across tasks, grapheme-to-phoneme conversion results in the most human-like character embeddings. Finally, ELMo embeddings differ from both humans and other models."
}