@inproceedings{wu-etal-2024-homophone2vec,
    title = "{H}omophone2{V}ec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity",
    author = "Wu, Sophie  and
      Zheng, Anita  and
      Chuang, Joey",
    editor = "Fu, Xiyan  and
      Fleisig, Eve",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-srw.34/",
    doi = "10.18653/v1/2024.acl-srw.34",
    pages = "287--292",
    ISBN = "979-8-89176-097-4",
    abstract = "This paper introduces a novel method for empirically evaluating the relationship between the phonological and semantic similarity of linguistic units using embedding spaces. Chinese character homophones are used as a proof-of-concept. We employ cosine similarity as a proxy for semantic similarity between characters, and compare relationships between phonologically-related characters and baseline characters (chosen as similar-frequency characters). We show there is a strongly statistically significant positive semantic relationship among different Chinese characters at varying levels of sound-sharing. We also perform some basic probing using t-SNE and UMAP visualizations, and indicate directions for future applications of this method."
}