Affordance Extraction and Inference based on Semantic Role Labeling
This addresses the need for interpretable common-sense reasoning in NLP, though it appears incremental as it builds on existing hypotheses.
The paper tackles the problem of common-sense reasoning in NLP by proposing an explicit word representation based on semantic roles and affordances, which improves state-of-the-art on unsupervised word similarity tasks and enables direct inference of new relations.
Common-sense reasoning is becoming increasingly important for the advancement of Natural Language Processing. While word embeddings have been very successful, they cannot explain which aspects of 'coffee' and 'tea' make them similar, or how they could be related to 'shop'. In this paper, we propose an explicit word representation that builds upon the Distributional Hypothesis to represent meaning from semantic roles, and allow inference of relations from their meshing, as supported by the affordance-based Indexical Hypothesis. We find that our model improves the state-of-the-art on unsupervised word similarity tasks while allowing for direct inference of new relations from the same vector space.