Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
arXiv:1812.11321
Abstract
A capsule is a group of neurons, whose activity vector represents the instantiation parameters of a specific type of entity. In this paper, we explore the capsule networks used for relation extraction in a multi-instance multi-label learning framework and propose a novel neural approach based on capsule networks with attention mechanisms. We evaluate our method with different benchmarks, and it is demonstrated that our method improves the precision of the predicted relations. Particularly, we show that capsule networks improve multiple entity pairs relation extraction.
To be published in EMNLP 2018
References in corpus (8)
- A Structured Self-attentive Sentence Embedding
- Cross-Sentence N-ary Relation Extraction with Graph LSTMs
- Classifying Relations by Ranking with Convolutional Neural Networks
- Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention
- Investigating Capsule Networks with Dynamic Routing for Text Classification
- Information Aggregation via Dynamic Routing for Sequence Encoding
- SEE: Syntax-aware Entity Embedding for Neural Relation Extraction
- Ensemble Neural Relation Extraction with Adaptive Boosting
Cited by in corpus (9)
- Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
- Deep Neural Network Based Relation Extraction: An Overview
- A Capsule Network for Recommendation and Explaining What You Like and Dislike
- Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification
- RDSGAN: Rank-based Distant Supervision Relation Extraction with Generative Adversarial Framework
- Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
- Context-aware Deep Model for Entity Recommendation in Search Engine at Alibaba
- Sequential Routing Framework: Fully Capsule Network-based Speech Recognition
- Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network