Multi-Relation Extraction in Entity Pairs using Global Context

TL;DR

This paper presents a novel global context embedding method for document-level relation extraction, capturing entity relationships across entire documents to improve accuracy over previous sentence-focused approaches.

Contribution

It introduces a new input encoding technique that models global relationships and multi-sentence reasoning for more accurate document-level relation extraction.

Findings

Improved relation prediction accuracy on benchmark datasets

Effective modeling of global context and multi-sentence reasoning

Enhanced performance over previous sentence-focused methods

Abstract

In document-level relation extraction, entities may appear multiple times in a document, and their relationships can shift from one context to another. Accurate prediction of the relationship between two entities across an entire document requires building a global context spanning all relevant sentences. Previous approaches have focused only on the sentences where entities are mentioned, which fails to capture the complete document context necessary for accurate relation extraction. Therefore, this paper introduces a novel input embedding approach to capture the positions of mentioned entities throughout the document rather than focusing solely on the span where they appear. The proposed input encoding approach leverages global relationships and multi-sentence reasoning by representing entities as standalone segments, independent of their positions within the document. The performance of the proposed method has been tested on three benchmark relation extraction datasets, namely DocRED, Re-DocRED, and REBEL. The experimental results demonstrated that the proposed method accurately predicts relationships between entities in a document-level setting. The proposed research also has theoretical and practical implications. Theoretically, it advances global context modeling and multi-sentence reasoning in document-level relation extraction. Practically, it enhances relationship detection, enabling improved performance in real-world NLP applications requiring comprehensive entity-level insights and interpretability.