@inproceedings{lawley-schubert-2022-mining,
    title = "Mining Logical Event Schemas From Pre-Trained Language Models",
    author = "Lawley, Lane  and
      Schubert, Lenhart",
    editor = "Louvan, Samuel  and
      Madotto, Andrea  and
      Madureira, Brielen",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.acl-srw.25/",
    doi = "10.18653/v1/2022.acl-srw.25",
    pages = "332--345",
    abstract = "We present NESL (the Neuro-Episodic Schema Learner), an event schema learning system that combines large language models, FrameNet parsing, a powerful logical representation of language, and a set of simple behavioral schemas meant to bootstrap the learning process. In lieu of a pre-made corpus of stories, our dataset is a continuous feed of {\textquotedblleft}situation samples{\textquotedblright} from a pre-trained language model, which are then parsed into FrameNet frames, mapped into simple behavioral schemas, and combined and generalized into complex, hierarchical schemas for a variety of everyday scenarios. We show that careful sampling from the language model can help emphasize stereotypical properties of situations and de-emphasize irrelevant details, and that the resulting schemas specify situations more comprehensively than those learned by other systems."
}