Classifying Relations by Ranking with Convolutional Neural Networks
arXiv:1504.06580
Abstract
Relation classification is an important semantic processing task for which state-ofthe-art systems still rely on costly handcrafted features. In this work we tackle the relation classification task using a convolutional neural network that performs classification by ranking (CR-CNN). We propose a new pairwise ranking loss function that makes it easy to reduce the impact of artificial classes. We perform experiments using the the SemEval-2010 Task 8 dataset, which is designed for the task of classifying the relationship between two nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art for this dataset and achieve a F1 of 84.1 without using any costly handcrafted features. Additionally, our experimental results show that: (1) our approach is more effective than CNN followed by a softmax classifier; (2) omitting the representation of the artificial class Other improves both precision and recall; and (3) using only word embeddings as input features is enough to achieve state-of-the-art results if we consider only the text between the two target nominals.
Accepted as a long paper in the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015)
References in corpus (1)
Cited by in corpus (11)
- Cross-Sentence N-ary Relation Extraction with Graph LSTMs
- Challenges in Data-to-Document Generation
- Improved Neural Relation Detection for Knowledge Base Question Answering
- Neural Models for Sequence Chunking
- Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion
- A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features
- Brain Intelligence: Go Beyond Artificial Intelligence
- Exploring Different Dimensions of Attention for Uncertainty Detection
- Multiple Range-Restricted Bidirectional Gated Recurrent Units with Attention for Relation Classification
- Modeling Semantic Relatedness using Global Relation Vectors
- Improved Knowledge Base Completion by Path-Augmented TransR Model