Actively Supervised Clustering for Open Relation Extraction

by   Jun Zhao, et al.
FUDAN University

Current clustering-based Open Relation Extraction (OpenRE) methods usually adopt a two-stage pipeline. The first stage simultaneously learns relation representations and assignments. The second stage manually labels several instances and thus names the relation for each cluster. However, unsupervised objectives struggle to optimize the model to derive accurate clustering assignments, and the number of clusters has to be supplied in advance. In this paper, we present a novel setting, named actively supervised clustering for OpenRE. Our insight lies in that clustering learning and relation labeling can be alternately performed, providing the necessary guidance for clustering without a significant increase in human effort. The key to the setting is selecting which instances to label. Instead of using classical active labeling strategies designed for fixed known classes, we propose a new strategy, which is applicable to dynamically discover clusters of unknown relations. Experimental results show that our method is able to discover almost all relational clusters in the data and improve the SOTA methods by 10.3% and 5.2%, on two datasets respectively.


page 1

page 2

page 3

page 4


A Relation-Oriented Clustering Method for Open Relation Extraction

The clustering-based unsupervised relation discovery method has graduall...

Active Relation Discovery: Towards General and Label-aware Open Relation Extraction

Open Relation Extraction (OpenRE) aims to discover novel relations from ...

Open Set Relation Extraction via Unknown-Aware Training

The existing supervised relation extraction methods have achieved impres...

SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction

Open relation extraction is the task of extracting open-domain relation ...

PromptORE – A Novel Approach Towards Fully Unsupervised Relation Extraction

Unsupervised Relation Extraction (RE) aims to identify relations between...

A Novel Few-Shot Relation Extraction Pipeline Based on Adaptive Prototype Fusion

Few-shot relation extraction (FSRE) aims at recognizing unseen relations...

Discovering Human Interactions in Videos with Limited Data Labeling

We present a novel approach for discovering human interactions in videos...

Please sign up or login with your details

Forgot password? Click here to reset