Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, Dongyan Zhao
Abstract
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassingly simple but effective method to heuristically select evidence sentences for document-level RE, which can be easily combined with BiLSTM to achieve good performance on benchmark datasets, even better than fancy graph neural network based methods. We have released our code at https://github.com/AndrewZhe/Three-Sentences-Are-All-You-Need.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Relation Extraction | DocRED | F1 | 56.23 | Paths+BiLSTM-GloVe |
Related Papers
Modeling Code: Is Text All You Need?2025-07-15All Eyes, no IMU: Learning Flight Attitude from Vision Alone2025-07-15DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations2025-07-08Is Diversity All You Need for Scalable Robotic Manipulation?2025-07-08DESIGN AND IMPLEMENTATION OF ONLINE CLEARANCE REPORT.2025-07-07Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models2025-07-03Prompt2SegCXR:Prompt to Segment All Organs and Diseases in Chest X-rays2025-07-01State and Memory is All You Need for Robust and Reliable AI Agents2025-06-30