A neural network-based joint learning approach for biomedical entity and relation extraction from biomedical literature

Now-a-days, people around the world are infected by many new diseases. The cost of developing or discovering a new drug for the newly discovered disease is very high and prolonged process. These could be eliminated with the help of already existing resources. To identify the candidates from the existing drugs, we need to extract the relation between the drug, target and disease by textming a large-scale literature. Recently, computational approaches which is used for identifying the relationships between the entities in biomedical domain are appearing as an active area of research for drug discovery as it needs more man power. Due to the limited computational approaches, the relation extraction between drug-gene and genedisease association from the unstructured biomedical documents is very hard. In this work, we proposed a semi-supervised approach named pattern based bootstrapping method to extract the direct relations between drug, gene and disease from the biomedical literature. These direct relationships are used to infer indirect relationships between entities such as drug and disease. Now these indirect relationships are used to determine the new candidates for drug repositioning which in turn will reduce the time and the patient’s risk.

Download Full-text

Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

Monte Carlo Methods and Applications ◽

10.1515/mcma-2020-2080 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Idris Kharroubi ◽

Thomas Lim ◽

Xavier Warin

Keyword(s):

Neural Network ◽

Machine Learning ◽

Neural Networks ◽

Differential Equations ◽

Numerical Experiments ◽

Optimization Problem ◽

Learning Approach ◽

The Neural Network ◽

Machine Learning Approach ◽

Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Download Full-text

Multi-directional temporal convolutional artificial neural network for PM2.5 forecasting with missing values: A deep learning approach

Urban Climate ◽

10.1016/j.uclim.2021.100800 ◽

2021 ◽

Vol 36 ◽

pp. 100800

Author(s):

K. Krishna Rani Samal ◽

Korra Sathya Babu ◽

Santos Kumar Das

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Deep Learning ◽

Missing Values ◽

Learning Approach ◽

Artificial Neural

Download Full-text

Populating Web-Scale Knowledge Graphs Using Distantly Supervised Relation Extraction and Validation

Information ◽

10.3390/info12080316 ◽

2021 ◽

Vol 12 (8) ◽

pp. 316

Author(s):

Sarthak Dash ◽

Michael R. Glass ◽

Alfio Gliozzo ◽

Mustafa Canim ◽

Gaetano Rossiello

Keyword(s):

Deep Learning ◽

Relation Extraction ◽

Automated System ◽

External Information ◽

Learning Approach ◽

Wide Margin ◽

Structure Information ◽

Adaptation Cost ◽

Knowledge Graphs ◽

Scale Experiment

In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep-learning-based technology for relation extraction that can be trained by a distantly supervised approach. In addition, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations. The designed system does not require any effort for adaptation to new languages and domains as it does not use any hand-labeled data, NLP analytics, and inference rules. Our experiments, performed on a popular academic benchmark, demonstrate that the suggested system boosts the performance of relation extraction by a wide margin, reporting error reductions of 50%, resulting in relative improvement of up to 100%. Furthermore, a web-scale experiment conducted to extend DBPedia with knowledge from Common Crawl shows that our system is not only scalable but also does not require any adaptation cost, while yielding a substantial accuracy gain.

Download Full-text