A5103207412- Topic Modeling
- Natural Language Processing Techniques
- Biomedical Text Mining and Ontologies
- Text and Document Classification Technologies
- Phonocardiography and Auscultation Techniques
- Engineering Education and Technology
- Lung Cancer Diagnosis and Treatment
- Cognitive Science and Mapping
- Discourse Analysis and Cultural Communication
- Venous Thromboembolism Diagnosis and Management
- Speech and dialogue systems
- Human-Automation Interaction and Safety
- Machine Learning in Healthcare
- Financial Distress and Bankruptcy Prediction
Nankai University
2024
Jingdong (China)
2022
Shanghai University of Engineering Science
2020
Shanghai University
2019
Arizona State University
2011
Hongyan Xie, Haoxiang Su, Shuangyong Song, Hao Huang, Bo Zou, Kun Deng, Jianghua Lin, Zhihui Zhang, Xiaodong He. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.
Pulmonary embolism is a common cardiovascular emergency with about 600,000 cases occurring annually and causing approximately 200,000 deaths in the US. CT pulmonary angiography (CTPA) has become reference standard for PE diagnosis, but interpretation of these large image datasets made complex time consuming by intricate branching structure vessels, myriad artifacts that may obscure or mimic PEs, suboptimal bolus contrast inhomogeneities arterial blood pool. To meet this challenge, several...
Named Entity Recognition (NER) on Clinical Electronic Medical Records (CEMR) is a fundamental step in extracting disease knowledge by identifying specific entity terms such as diseases, symptoms, etc. However, the state-of-the-art NER methods based Long Short-Term Memory (LSTM) fail to exploit GPU parallelism fully under massive medical records. Although novel method Iterated Dilated CNNs (ID-CNNs) can accelerate network computing, it tends ignore word-order feature and semantic information...
Relation classification is the task of identifying relations between two entities in a sentence, which an essential step standard NLP pipeline. Most previous models only make use dependency or semantic features, may result loss vital information. In this paper, we propose novel model that incorporates and information for relation classification. This neural network using long short-term memory(LSTM), graph convolutional networks(GCN), networks(CNN), named LGCNN. Concretely, it utilizes...
To model bankruptcy prediction of listed companies, wefirst propose a novel machine learning method buildingnaïve Bayesian networks (NBNs) based on minimumdescription-length (MDL) principle, and then use thefinancial ratio data a-share companies from 2002to 2009 in China to test its feasibility validation.