期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：2673-2685
DOI：10.18653/v1/2021.eacl-main.230
语种：English
出版社：ACL Anthology
摘要：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.
