scholarly journals Relation extraction using label propagation based semi-supervised learning

2006 ◽  
Author(s):  
Jinxiu Chen ◽  
Donghong Ji ◽  
Chew Lim Tan ◽  
Zhengyu Niu
Keyword(s):  
Supervised Learning ◽  
Relation Extraction ◽  
Label Propagation

A Hybrid Method Based on Semi-Supervised Learning for Relation Extraction in Chinese EMRs (Preprint)

2021 ◽  
Author(s):  
ChunMing Yang
Keyword(s):  
Supervised Learning ◽  
Learning Algorithm ◽  
Medical Knowledge ◽  
Relation Extraction ◽  
Small Scale ◽  
Semantic Features ◽  
Training Process ◽  
Network Layers ◽  
Relation Prediction ◽  
The Cost

BACKGROUND Extracting relations between the entities from Chinese electronic medical records(EMRs) is the key to automatically constructing medical knowledge graphs. Due to the less available labeled corpus, most of the current researches are based on shallow networks, which cannot fully capture the complex semantic features in the text of Chinese EMRs. OBJECTIVE In this study, a hybrid deep learning method based on semi-supervised learning is proposed to extract the entity relations from small-scale complex Chinese EMRs. METHODS The semantic features of sentences are extracted by residual network (ResNet) and the long dependent information is captured by bidirectional GRU (Gated Recurrent Unit). Then the attention mechanism is used to assign weights to the extracted features respectively, and the output of the two attention mechanisms is integrated for relation prediction. We adjusted the training process with manually annotated small-scale relational corpus and bootstrapping semi-supervised learning algorithm, and continuously expanded the datasets during the training process. RESULTS The experimental results show that the best F1-score of the proposed method on the overall relation categories reaches 89.78%, which is 13.07% higher than the baseline CNN model. The F1-score on DAP, SAP, SNAP, TeRD, TeAP, TeCP, TeRS, TeAS, TrAD, TrRD and TrAP 11 relation categories reaches 80.95%, 93.91%, 92.96%, 88.43%, 86.54%, 85.58%, 87.96%, 94.74%, 93.01%, 87.58% and 95.48%, respectively. CONCLUSIONS The hybrid neural network method strengthens the feature transfer and reuse between different network layers and reduces the cost of manual tagging relations. The results demonstrate that our proposed method is effective for the relation extraction in Chinese EMRs.

Label Propagation Algorithm for the Slices Detection of a Ground-Glass Opacity Nodule

2019 ◽  
Vol 7 (1) ◽  
pp. 104-118 ◽  
Author(s):  
Weiwei Du ◽  
Dandan Yuan ◽  
Jianming Wang ◽  
Xiaojie Duan ◽  
Yanhe Ma ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Lung Tumor ◽  
Ground Glass Opacity ◽  
Label Propagation ◽  
Ground Glass ◽  
Volume Data ◽  
Propagation Algorithm ◽  
Benign Lung Tumor ◽  
The Impact ◽  
Ct Volume

A radiologist must read hundreds of slices to recognize a malignant or benign lung tumor in computed tomography (CT) volume data. To reduce the burden of the radiologist, some proposals have been applied with the ground-glass opacity (GGO) nodules. However, the GGO nodules need be detected and labeled by a radiologist manually. Some slices with the GGO nodule can be missed because there are many slices in several volume data. Although some papers have proposed a semi-supervised learning method to find the slices with GGO nodules, the was no discussion on the impact of parameters in the proposed semi-supervised learning. This article also explains and analyzes the label propagation algorithm which is one of the semi-supervised learning methods to detect the slices including the GGO nodules based on the parameters. Experimental results show that the proposal can detect the slices including the GGO nodules effectively.

scholarly journals Supervised learning is an accurate method for network-based gene classification

2020 ◽  
Vol 36 (11) ◽  
pp. 3457-3465 ◽  
Author(s):  
Renming Liu ◽  
Christopher A Mancuso ◽  
Anna Yannakopoulos ◽  
Kayla A Johnson ◽  
Arjun Krishnan
Keyword(s):  
Supervised Learning ◽  
Network Connectivity ◽  
Accurate Method ◽  
Label Propagation ◽  
Local Network ◽  
Supplementary Information ◽  
Grand Challenge ◽  
Disease Associated Genes ◽  
Propagation Technique ◽  
Full Network

Abstract Background Assigning every human gene to specific functions, diseases and traits is a grand challenge in modern genetics. Key to addressing this challenge are computational methods, such as supervised learning and label propagation, that can leverage molecular interaction networks to predict gene attributes. In spite of being a popular machine-learning technique across fields, supervised learning has been applied only in a few network-based studies for predicting pathway-, phenotype- or disease-associated genes. It is unknown how supervised learning broadly performs across different networks and diverse gene classification tasks, and how it compares to label propagation, the widely benchmarked canonical approach for this problem. Results In this study, we present a comprehensive benchmarking of supervised learning for network-based gene classification, evaluating this approach and a classic label propagation technique on hundreds of diverse prediction tasks and multiple networks using stringent evaluation schemes. We demonstrate that supervised learning on a gene’s full network connectivity outperforms label propagaton and achieves high prediction accuracy by efficiently capturing local network properties, rivaling label propagation’s appeal for naturally using network topology. We further show that supervised learning on the full network is also superior to learning on node embeddings (derived using node2vec), an increasingly popular approach for concisely representing network connectivity. These results show that supervised learning is an accurate approach for prioritizing genes associated with diverse functions, diseases and traits and should be considered a staple of network-based gene classification workflows. Availability and implementation The datasets and the code used to reproduce the results and add new gene classification methods have been made freely available. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals A note on label propagation for semi-supervised learning

2015 ◽  
Vol 7 (1) ◽  
pp. 18-30
Author(s):  
Zalán Bodó ◽  
Lehel Csató
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Unlabeled Data ◽  
Label Propagation ◽  
Learning Method ◽  
The Past ◽  
Data Graph

Abstract Semi-supervised learning has become an important and thoroughly studied subdomain of machine learning in the past few years, because gathering large unlabeled data is almost costless, and the costly human labeling process can be minimized by semi-supervision. Label propagation is a transductive semi-supervised learning method that operates on the—most of the time undirected—data graph. It was introduced in [8] and since many variants were proposed. However, the base algorithm has two variants: the first variant presented in [8] and its slightly modified version used afterwards, e.g. in [7]. This paper presents and compares the two algorithms—both theoretically and experimentally—and also tries to make a recommendation which variant to use.

Iterative Label Propagation Based on Semi-Supervised Learning for Classifying Benign and Malignant Pulmonary Nodules

2018 ◽  
Vol 8 (7) ◽  
pp. 1456-1461
Author(s):  
Xiangxia Li ◽  
Bin Li ◽  
Lianfang Tian ◽  
Li Zhang ◽  
Guangming Peng ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Pulmonary Nodules ◽  
Label Propagation
Sign in / Sign up

Export Citation Format

Share Document