Earticle

초록

영어

Many machine learning methods have been applied on the biomedical named entity recognition and achieve good results on GENIA corpus. However most of those methods reply on the feature engineering which is labor-intensive. In this paper，huge potential feature information represented as word vectors are generated by neutral networks based on unlabeled biomedical text files. We propose a Biomedical Named Entity Recognition (Bio-NER) method based on deep neural network architecture which has multiple layers and each layer abstracts features based upon the features generated by lower layers. Our system achieved F-score 71.01% on GENIA regular test corpus , F-score values for 5-fold cross-validation is 71.01% and this result is closed to the state-of-the-art performance with only POS (Part-of-speech) feature and represents the deep learning can effectively performed on biomedical NER.

목차

Abstract
 1. Introduction
 2. Architecture
  2.1. Extracting Word Feature Vectors
  2.2. Extracting Sentence Level Features
  2.3. Label Criterion
  2.4. Stochastic Gradient
 3. Experiments
  3.1. Task Description
  3.2. Experiment Result and Analysis
 4. Conclusion
 References

키워드

저자

• Lin Yao [ School of Electronics Engineering and Computer Science, Peking University, Pku-hkust Shenzhen-hongkong Institution, School of Software, HIT ]
• Hong Liu [ School of Electronics Engineering and Computer Science, Peking University ]
• Yi Liu [ Pku-hkust Shenzhen-hongkong Institution ]
• Xinxin Li [ Computer Science Department, HITSGS ]
• Muhammad Waqas Anwar [ Department of Computer Science, COMSATS Institute of Information Technology ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605