Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration
Open relation extraction is the task to extract relational facts without pre-defined relation types from open-domain corpora. However, since there are some hard or semi-hard instances sharing similar context and entity information but belonging to different underlying relation, current OpenRE methods always cluster them into the same relation type. In this paper, we propose a novel method based on Instance Ranking and Label Calibration strategies (IRLC) to learn discriminative representations for open relation extraction. Due to lacking the original instance label, we provide three surrogate strategies to generate the positive, hard negative, and semi-hard negative instances for the original instance. Instance ranking aims to refine the relational feature space by pushing the hard and semi-hard negative instances apart from the original instance with different margins and pulling the original instance and its positive instance together. To refine the cluster probability distributions of these instances, we introduce a label calibration strategy to model the constraint relationship between instances. Experimental results on two public datasets demonstrate that our proposed method can significantly outperform the previous state-of-the-art methods.
Code (1)
Tasks
RelationRelation ExtractionSimilar Papers 제목 키워드 기반
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning
Differentiating relationships between entity pairs with limited labeled instances poses a significant challenge in few-shot relation classification. Representations of textual data extract rich information spanning the d…
ClassificationContrastive LearningFew-Shot Relation ClassificationRelation+3ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable ge…
Relation ExtractionAbstains from Prediction: Towards Robust Relation Extraction in Real World
“Supervised learning is a classic paradigm of relation extraction (RE). However, a well-performing model can still confidently make arbitrarily wrong predictions when exposed to samples of unseen relations. In this work,…
Contrastive LearningRelationRelation ExtractionRelation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
Pre-trained language models have contributed significantly to relation extraction by demonstrating remarkable few-shot learning abilities. However, prompt tuning methods for relation extraction may still fail to generali…
Few-Shot LearningMemorizationRelationRelation Extraction+1Actively Supervised Clustering for Open Relation Extraction
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 seve…
ClusteringRelationRelation Extraction