FrameNet Semantic Role Classification by Analogy
This provides an efficient method for semantic role labeling in natural language processing, though it appears incremental as it builds on existing FrameNet frameworks.
The paper tackles Semantic Role Classification in FrameNet by reformulating it as a binary classification problem using analogical relations between lexical units and frame elements, achieving state-of-the-art results with computational efficiency.
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.