SynsetRank: Degree-adjusted Random Walk for Relation Identification

TL;DR

This paper introduces SynsetRank, a novel degree-adjusted random walk method that improves relation detection by effectively utilizing semantic graph structures like BabelNet, outperforming previous approaches.

Contribution

SynsetRank enhances random walk algorithms by adjusting initial probabilities based on node degree, leading to better relation identification in semantic graphs.

Findings

SynsetRank significantly outperforms baseline methods.

Adjusting for node degree improves relation detection accuracy.

The method is effective across multiple relation types.

Abstract

In relation extraction, a key process is to obtain good detectors that find relevant sentences describing the target relation. To minimize the necessity of labeled data for refining detectors, previous work successfully made use of BabelNet, a semantic graph structure expressing relationships between synsets, as side information or prior knowledge. The goal of this paper is to enhance the use of graph structure in the framework of random walk with a few adjustable parameters. Actually, a straightforward application of random walk degrades the performance even after parameter optimization. With the insight from this unsuccessful trial, we propose SynsetRank, which adjusts the initial probability so that high degree nodes influence the neighbors as strong as low degree nodes. In our experiment on 13 relations in the FB15K-237 dataset, SynsetRank significantly outperforms baselines and the plain random walk approach.