Zero-shot Relation Classification from Side Information

TL;DR

This paper introduces ZSLRC, a zero-shot relation classification framework that leverages side information and advanced prototypical networks to recognize unseen relations, outperforming existing methods across various learning scenarios.

Contribution

The paper presents a novel zero-shot relation classification method using weighted side information and hypernym extraction, significantly improving recognition of unseen relations.

Findings

Outperforms state-of-the-art methods on NYT and FewRel datasets.

Effective in supervised, few-shot, and zero-shot learning tasks.

Demonstrates robustness and practical applicability in real-world scenarios.

Abstract

We propose a zero-shot learning relation classification (ZSLRC) framework that improves on state-of-the-art by its ability to recognize novel relations that were not present in training data. The zero-shot learning approach mimics the way humans learn and recognize new concepts with no prior knowledge. To achieve this, ZSLRC uses advanced prototypical networks that are modified to utilize weighted side (auxiliary) information. ZSLRC's side information is built from keywords, hypernyms of name entities, and labels and their synonyms. ZSLRC also includes an automatic hypernym extraction framework that acquires hypernyms of various name entities directly from the web. ZSLRC improves on state-of-the-art few-shot learning relation classification methods that rely on labeled training data and is therefore applicable more widely even in real-world scenarios where some relations have no corresponding labeled examples for training. We present results using extensive experiments on two public datasets (NYT and FewRel) and show that ZSLRC significantly outperforms state-of-the-art methods on supervised learning, few-shot learning, and zero-shot learning tasks. Our experimental results also demonstrate the effectiveness and robustness of our proposed model.