Thumbnails:
List:
Year:
Category:
Session:
Poster:
Getting poster data...
Vivek Kumar Srivastav, Angela Kranz and and Björn Usadel (Forschungszentrum Jülich, Wilhelm-Johnen-Straße, 52428 Jülich, Germany)
Extracting biological data from scientific journals is an important task, but various current techniques are limited to summaries only. However, online access to the entire article can provide more comprehensive research material. However, whether it's worthwhile to read entire articles and extract information from their many parts is still controversial. One approach to this task is so-called "literature mining," which involves collecting and analyzing data from scientific papers. In recent years, many computational systems aimed at extracting molecular biology data have been developed, including smarter machine learning-based approaches that require a large amount of labeled data. To address this challenge, we present a supervised framework for information extraction based on the recommendations of MIAPPE, ISA-Tab, MiXs, MIAME, MIICA, MIACME, and MINSEQE. Our proposed system uses a combination of convolutional neural networks (CNNs), natural language processing (NLP), and machine learning.