@inproceedings{oyama-etal-2024-understanding,
    title = "Understanding Higher-Order Correlations Among Semantic Components in Embeddings",
    author = "Oyama, Momose  and
      Yamagiwa, Hiroaki  and
      Shimodaira, Hidetoshi",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2024.emnlp-main.169/",
    doi = "10.18653/v1/2024.emnlp-main.169",
    pages = "2883--2899",
    abstract = "Independent Component Analysis (ICA) offers interpretable semantic components of embeddings.While ICA theory assumes that embeddings can be linearly decomposed into independent components, real-world data often do not satisfy this assumption. Consequently, non-independencies remain between the estimated components, which ICA cannot eliminate. We quantified these non-independencies using higher-order correlations and demonstrated that when the higher-order correlation between two components is large, it indicates a strong semantic association between them, along with many words sharing common meanings with both components. The entire structure of non-independencies was visualized using a maximum spanning tree of semantic components. These findings provide deeper insights into embeddings through ICA."
}