Multi-labeled Relation Extraction with Attentive Capsule Network
arXiv:1811.04354
Abstract
To disclose overlapped multiple relations from a sentence still keeps challenging. Most current works in terms of neural models inconveniently assuming that each sentence is explicitly mapped to a relation label, cannot handle multiple relations properly as the overlapped features of the relations are either ignored or very difficult to identify. To tackle with the new issue, we propose a novel approach for multi-labeled relation extraction with capsule network which acts considerably better than current convolutional or recurrent net in identifying the highly overlapped relations within an individual sentence. To better cluster the features and precisely extract the relations, we further devise attention-based routing algorithm and sliding-margin loss function, and embed them into our capsule network. The experimental results show that the proposed approach can indeed extract the highly overlapped features and achieve significant performance improvement for relation extraction comparing to the state-of-the-art works.
arXiv commentTo be published in AAAI 2019
References in corpus (9)
- Efficient Estimation of Word Representations in Vector Space
- Relation Classification via Recurrent Neural Network
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
- Capsule Network Performance on Complex Data
- Classifying Relations by Ranking with Convolutional Neural Networks
- Combining Neural Networks and Log-linear Models to Improve Relation Extraction
- Neural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning
- Ensemble Neural Relation Extraction with Adaptive Boosting
- Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network