Learning Graph Embeddings from WordNet-based Similarity Measures
This work addresses graph embedding for semantic tasks, but it is incremental as it builds on existing similarity measures and methods.
The authors tackled the problem of learning graph embeddings by introducing path2vec, which approximates user-defined graph distance measures like shortest path distance, and showed competitive results on semantic similarity and word sense disambiguation tasks using WordNet-based measures, outperforming strong baselines and being orders of magnitude faster.
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph embedding baselines. The model is computationally efficient, being orders of magnitude faster than the direct computation of graph-based distances.