@inproceedings{van-boven-bloem-2022-domain,
    title = "Domain-specific Evaluation of Word Embeddings for Philosophical Text using Direct Intrinsic Evaluation",
    author = "van Boven, Goya  and
      Bloem, Jelke",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Alnajjar, Khalid  and
      Partanen, Niko  and
      Rueter, Jack},
    booktitle = "Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities",
    month = nov,
    year = "2022",
    address = "Taipei, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.nlp4dh-1.14/",
    doi = "10.18653/v1/2022.nlp4dh-1.14",
    pages = "101--107",
    abstract = "We perform a direct intrinsic evaluation of word embeddings trained on the works of a single philosopher. Six models are compared to human judgements elicited using two tasks: a synonym detection task and a coherence task. We apply a method that elicits judgements based on explicit knowledge from experts, as the linguistic intuition of non-expert participants might differ from that of the philosopher. We find that an in-domain SVD model has the best 1-nearest neighbours for target terms, while transfer learning-based Nonce2Vec performs better for low frequency target terms."
}