FrameNet Semantic Role Classification by Analogy

Van Duy Ngo, Stergos Afantenos, Emiliano Lorini, Miguel Couceiro


Abstract
In this paper, we adopt a relational view of analogies applied to Semantic Role Classification in FrameNet. We define analogies as formal relations over the Cartesian product of frame evoking lexical units and frame element pairs, which we use to construct a new dataset.Each element of this binary relation is labelled as a valid analogical instance if the frame elements share the same semantic role, or as invalid otherwise.This formulation allows us to transform Semantic Role Classification into binary classification and train a lightweight Artificial Neural Network (ANN) that exhibits rapid convergence with minimal parameters. Crucially, no Semantic Role information is introduced to the neural network during training. We recover semantic roles during inference by computing probability distributions over candidates of all semantic roles within a given frame through random sampling and analogical transfer. This approach allows us to surpass previous State of the Art results while maintaining computational efficiency and frugality.
Anthology ID:
2026.lrec-1.291
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
3633–3644
Language:
External URL:
https://lrec.elra.info/lrec2026-main-291
DOI:
10.63317/4orqo3vca85v
Bibkey:
Cite (ACL):
Van Duy Ngo, Stergos Afantenos, Emiliano Lorini, and Miguel Couceiro. 2026. FrameNet Semantic Role Classification by Analogy. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3633–3644, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
FrameNet Semantic Role Classification by Analogy (Ngo et al., LREC 2026)
Copy Citation: