ACL 2022long21 citations

Learning Disentangled Representations of Negation and Uncertainty

Jake Vasilakes, Chrysoula Zerva, Makoto Miwa, Sophia Ananiadou

Abstract

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify. However, previous works on representation learning do not explicitly model this independence. We therefore attempt to disentangle the representations of negation, uncertainty, and content using a Variational Autoencoder. We find that simply supervising the latent representations results in good disentanglement, but auxiliary objectives based on adversarial learning and mutual information minimization can provide additional disentanglement gains.

BibTeX
@inproceedings{vasilakes-etal-2022-learning,
    title = "Learning Disentangled Representations of Negation and Uncertainty",
    author = "Vasilakes, Jake  and
      Zerva, Chrysoula  and
      Miwa, Makoto  and
      Ananiadou, Sophia",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.574/",
    doi = "10.18653/v1/2022.acl-long.574",
    pages = "8380--8397"
}