CLIRMay 22, 2024

Knowledge-Driven Cross-Document Relation Extraction

arXiv:2405.13546v227 citationsh-index: 29ACL
Originality Incremental advance
AI Analysis

This addresses the problem of linking findings from disparate documents for knowledge discovery in domains like biomedicine, representing an incremental advance.

The paper tackles cross-document relation extraction by incorporating domain knowledge of entities with input text, resulting in improved performance over prior methods and offering interpretability through explanatory text.

Relation extraction (RE) is a well-known NLP application often treated as a sentence- or document-level task. However, a handful of recent efforts explore it across documents or in the cross-document setting (CrossDocRE). This is distinct from the single document case because different documents often focus on disparate themes, while text within a document tends to have a single goal. Linking findings from disparate documents to identify new relationships is at the core of the popular literature-based knowledge discovery paradigm in biomedicine and other domains. Current CrossDocRE efforts do not consider domain knowledge, which are often assumed to be known to the reader when documents are authored. Here, we propose a novel approach, KXDocRE, that embed domain knowledge of entities with input text for cross-document RE. Our proposed framework has three main benefits over baselines: 1) it incorporates domain knowledge of entities along with documents' text; 2) it offers interpretability by producing explanatory text for predicted relations between entities 3) it improves performance over the prior methods.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes