@inproceedings{samih-kallmeyer-2023-unsupervised,
    title = "Unsupervised Semantic Frame Induction Revisited",
    author = "Samih, Younes  and
      Kallmeyer, Laura",
    editor = "Amblard, Maxime  and
      Breitholtz, Ellen",
    booktitle = "Proceedings of the 15th International Conference on Computational Semantics",
    month = jun,
    year = "2023",
    address = "Nancy, France",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.iwcs-1.10/",
    pages = "89--93",
    abstract = "This paper addresses the task of semantic frame induction based on pre-trained language models (LMs). The current state of the art is to directly use contextualized embeddings from models such as BERT and to cluster them in a two step clustering process (first lemma-internal, then over all verb tokens in the data set). We propose not to use the LM`s embeddings as such but rather to refine them via some transformer-based denoising autoencoder. The resulting embeddings allow to obtain competitive results while clustering them in a single pass. This shows clearly that the autoendocer allows to already concentrate on the information that is relevant for distinguishing event types."
}