Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention

Abstract

Relation extraction is the problem of classifying the relationship between two entities in a given sentence. Distant Supervision (DS) is a popular technique for developing relation extractors starting with limited supervision. We note that most of the sentences in the distant supervision relation extraction setting are very long and may benefit from word attention for better sentence representation. Our contributions in this paper are threefold. Firstly, we propose two novel word attention models for distantly- supervised relation extraction: (1) a Bi-directional Gated Recurrent Unit (Bi-GRU) based word attention model (BGWA), (2) an entity-centric attention model (EA), and (3) a combination model which combines multiple complementary models using weighted voting method for improved relation extraction. Secondly, we introduce GDS, a new distant supervision dataset for relation extraction. GDS removes test data noise present in all previous distant- supervision benchmark datasets, making credible automatic evaluation possible. Thirdly, through extensive experiments on multiple real-world datasets, we demonstrate the effectiveness of the proposed methods.

References in corpus (4)

• Scikit-learn: Machine Learning in Python
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Jointly Extracting Relations with Class Ties via Effective Deep Ranking
• CANDiS: Coupled & Attention-Driven Neural Distant Supervision

Cited by in corpus (18)

• Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
• Improving Neural Relation Extraction with Implicit Mutual Relations
• MatSciRE: Leveraging Pointer Networks to Automate Entity and Relation Extraction for Material Science Knowledge-base Construction
• Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
• Distantly Supervised Relation Extraction via Recursive Hierarchy-Interactive Attention and Entity-Order Perception
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction
• Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions
• Neural Graph Embedding Methods for Natural Language Processing
• Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
• RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
• Knodle: Modular Weakly Supervised Learning with PyTorch
• IPRE: a Dataset for Inter-Personal Relationship Extraction
• Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction
• Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction
• CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
• AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue
• Two Training Strategies for Improving Relation Extraction over Universal Graph