Document-Level Zero-Shot Relation Extraction with Entity Side Information

TL;DR

This paper presents a novel zero-shot relation extraction method that uses entity side information instead of LLM-generated data, improving accuracy especially for low-resource languages like Malaysian English.

Contribution

It introduces the DocZSRE-SI framework that leverages entity descriptions and hypernyms, achieving significant performance gains over existing LLM-based approaches.

Findings

11.6% average macro F1-Score improvement

Robustness in low-resource language contexts

Effective use of entity side information

Abstract

Document-Level Zero-Shot Relation Extraction (DocZSRE) aims to predict unseen relation labels in text documents without prior training on specific relations. Existing approaches rely on Large Language Models (LLMs) to generate synthetic data for unseen labels, which poses challenges for low-resource languages like Malaysian English. These challenges include the incorporation of local linguistic nuances and the risk of factual inaccuracies in LLM-generated data. This paper introduces Document-Level Zero-Shot Relation Extraction with Entity Side Information (DocZSRE-SI) to address limitations in the existing DocZSRE approach. The DocZSRE-SI framework leverages Entity Side Information, such as Entity Mention Descriptions and Entity Mention Hypernyms, to perform ZSRE without depending on LLM-generated synthetic data. The proposed low-complexity model achieves an average improvement of 11.6% in the macro F1-Score compared to baseline models and existing benchmarks. By utilizing Entity Side Information, DocZSRE-SI offers a robust and efficient alternative to error-prone, LLM-based methods, demonstrating significant advancements in handling low-resource languages and linguistic diversity in relation extraction tasks. This research provides a scalable and reliable solution for ZSRE, particularly in contexts like Malaysian English news articles, where traditional LLM-based approaches fall short.