Relation Classification as Two-way Span-Prediction

Amir DN Cohen, Shachar Rosenman, Yoav Goldberg

2020-10-09Question Answering Relation Extraction Prediction General Classification Classification Relation Classification Vocal Bursts Valence Prediction

Paper PDF

Abstract

The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.

Results

Task	Dataset	Metric	Value	Model
Relation Extraction	SemEval-2010 Task-8	F1	91.9	SP
Relation Extraction	TACRED	F1	74.8	Relation Reduction

Related Papers

Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction2025-07-21 From Roots to Rewards: Dynamic Tree Reasoning with RL2025-07-17 Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering2025-07-17 Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It2025-07-17 City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning2025-07-17 Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17 Describe Anything Model for Visual Question Answering on Text-rich Images2025-07-16 Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility2025-07-16