Improving Sentence-Level Relation Extraction through Curriculum Learning

Seongsik Park, Harksoo Kim

2021-07-20Relation Extraction
PaperPDF

Abstract

Sentence-level relation extraction mainly aims to classify the relation between two entities in a sentence. The sentence-level relation extraction corpus often contains data that are difficult for the model to infer or noise data. In this paper, we propose a curriculum learning-based relation extraction model that splits data by difficulty and utilizes them for learning. In the experiments with the representative sentence-level relation extraction datasets, TACRED and Re-TACRED, the proposed method obtained an F1-score of 75.0% and 91.4% respectively, which are the state-of-the-art performance.

Results

TaskDatasetMetricValueModel
Relation ExtractionTACREDF175EXOBRAIN
Relation ExtractionRe-TACREDF191.4EXOBRAIN

Related Papers

DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations2025-07-08Multiple Streams of Relation Extraction: Enriching and Recalling in Transformers2025-06-25Chaining Event Spans for Temporal Relation Grounding2025-06-17Summarization for Generative Relation Extraction in the Microbiome Domain2025-06-10Conservative Bias in Large Language Models: Measuring Relation Predictions2025-06-09Comparative Analysis of AI Agent Architectures for Entity Relationship Classification2025-06-03CREFT: Sequential Multi-Agent LLM for Character Relation Extraction2025-05-30Generating Diverse Training Samples for Relation Extraction with Large Language Models2025-05-29