@inproceedings{fukui-etal-2017-spectral,
    title = "Spectral Graph-Based Method of Multimodal Word Embedding",
    author = "Fukui, Kazuki  and
      Oshikiri, Takamasa  and
      Shimodaira, Hidetoshi",
    editor = "Riedl, Martin  and
      Somasundaran, Swapna  and
      Glava{\v{s}}, Goran  and
      Hovy, Eduard",
    booktitle = "Proceedings of {T}ext{G}raphs-11: the Workshop on Graph-based Methods for Natural Language Processing",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W17-2405/",
    doi = "10.18653/v1/W17-2405",
    pages = "39--44",
    abstract = "In this paper, we propose a novel method for multimodal word embedding, which exploit a generalized framework of multi-view spectral graph embedding to take into account visual appearances or scenes denoted by words in a corpus. We evaluated our method through word similarity tasks and a concept-to-image search task, having found that it provides word representations that reflect visual information, while somewhat trading-off the performance on the word similarity tasks. Moreover, we demonstrate that our method captures multimodal linguistic regularities, which enable recovering relational similarities between words and images by vector arithmetics."
}