« Back to all Projects

Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain

Implemented By:


We investigate a transfer scenario where we assume role-annotated data for the source verbal domain but only unlabeled data for the target nominal domain. Our key assumption, enabling the transfer between the two domains, is that selectional preferences of a role (i.e., preferences or constraints on the admissible arguments) do not strongly depend on whether the relation is triggered by a verb or a noun. For example, the same set of arguments can fill the Acquirer role for the verbal predicate acquire and its nominal form acquisition. We approach the transfer task from the variational autoencoding perspective.

  • Tags:
    • transfer learning
    • semantic role labeling
  • AllenNLP Version: 0.8.2
  • Languages: Unknown
  • Datasets:
  • Submitted On Sep 26, 2020