Affordance Extraction and Inference based on Semantic Role Labeling

TL;DR

This paper introduces a novel explicit word representation based on semantic roles that enhances unsupervised word similarity and enables direct inference of new relations, advancing common-sense reasoning in NLP.

Contribution

It proposes a new semantic role-based word embedding model that improves similarity tasks and supports relation inference, grounded in the affordance-based Indexical Hypothesis.

Findings

Improves state-of-the-art on unsupervised word similarity tasks.

Enables direct inference of new relations from the same vector space.

Supports better common-sense reasoning in NLP applications.

Abstract

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.