@inproceedings{breidenstein-labeau-2024-using,
    title = "Using Locally Learnt Word Representations for better Textual Anomaly Detection",
    author = "Breidenstein, Alicia  and
      Labeau, Matthieu",
    editor = "Tafreshi, Shabnam  and
      Akula, Arjun  and
      Sedoc, Jo{\~a}o  and
      Drozd, Aleksandr  and
      Rogers, Anna  and
      Rumshisky, Anna",
    booktitle = "Proceedings of the Fifth Workshop on Insights from Negative Results in NLP",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.insights-1.11/",
    doi = "10.18653/v1/2024.insights-1.11",
    pages = "82--91",
    abstract = "The literature on general purpose textual Anomaly Detection is quite sparse, as most textual anomaly detection methods are implemented as out of domain detection in the context of pre-established classification tasks. Notably, in a field where pre-trained representations and models are of common use, the impact of the pre-training data on a task that lacks supervision has not been studied. In this paper, we use the simple setting of k-classes out anomaly detection and search for the best pairing of representation and classifier. We show that well-chosen embeddings allow a simple anomaly detection baseline such as OC-SVM to achieve similar results and even outperform deep state-of-the-art models."
}