FrameNet Semantic Role Classification by Analogy

TL;DR

This paper introduces an analogy-based method for Semantic Role Classification in FrameNet, transforming the task into binary classification and achieving state-of-the-art results with a lightweight neural network.

Contribution

It presents a novel analogy-based approach that does not require semantic role information during training, enabling efficient and accurate semantic role inference.

Findings

Surpassed previous state-of-the-art accuracy

Achieved rapid convergence with minimal parameters

Maintained computational efficiency and simplicity

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 (LUs) and frame element (FEs) 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. Unconventionally, 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.