Recognizing Nested Named Entity Based on the Neural Network Boundary Assembling Model

The task to recognize named entities is often modeled as a sequence labeling process, which selects a label path whose probability is maximum for an input sentence. Because it makes the assumption that the input sentence has a flattened structure, it often fails to recognize nested named entities. In our previous work, a boundary assembling (BA) model was proposed. It is a cascading framework, which identifies named entity boundaries first, and then assembles them into entity candidates for further assessment. This model is effective to recognize nested named entities, but still suffers from poor performance caused by the sparse feature problem. In this article, the BA model is remodeled with the advancement of neural networks, which enables the model to capture semantic information of a sentence by using word embeddings pretrained in external resources. In our experiments, it shows an impressive improvement on the final performance, outperforming the state of the art more than 17% in F-score.

Authors

• Yanping Chen Guizhou University
• Yuefei Wu School of Computer Science and Technology, Xi’an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi’an Jiaotong University
• Yongbin Qin Guizhou University
• Ying Hu Department of Electronic Engineering, Tsinghua University
• Zeyu Wang The Hong Kong University of Science and Technology (Guangzhou) The Hong Kong University of Science and Technology
• Ruizhang Huang Guizhou University
• Xinyu Cheng Yale University, New Haven, United States
• Ping Chen

Keywords

• Task analysis
• Semantics
• Feature extraction
• Artificial neural networks
• Immune system
• Labeling
• Human computer interaction
• Neural Network
• Named Entity Recognition
• Parsing
• Semantic Information
• Event Detection
• External Resources
• Word Embedding
• Machine Translation
• Entity Types
• Bank Of China
• Sequence Labeling
• Cascade Model
• Input Sentence
• Parking Locations
• End Boundary
• Learning Rate
• Room For Improvement
• Recurrent Neural Network
• Dense Layer
• Layer Model
• Boundary Detection
• Pre-trained Word Embeddings
• Multilayer Perception
• Softmax Layer