Learning grounded word meaning representations on similarity graphs

TL;DR

This paper presents HM-SGE, a hierarchical graph embedding model that learns grounded word meanings across modalities, effectively capturing similarity relations and outperforming existing methods in simulating human judgments.

Contribution

The novel HM-SGE model integrates modality-specific and joint graph embeddings to improve grounded word meaning representations.

Findings

Outperforms state-of-the-art in simulating human similarity judgments

Effectively models concept categorization

Validates the hierarchical multi-modal graph approach

Abstract

This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific word representations through dedicated but communicating graphs, while the higher level puts these representations together on a single graph to learn a representation jointly from both modalities. The topology of each graph models similarity relations among words, and is estimated jointly with the graph embedding. The assumption underlying this model is that words sharing similar meaning correspond to communities in an underlying similarity graph in a low-dimensional space. We named this model Hierarchical Multi-Modal Similarity Graph Embedding (HM-SGE). Experimental results validate the ability of HM-SGE to simulate human similarity judgements and concept categorization, outperforming the state of the art.