Journal Article

Biomedical semantic indexing by deep neural network with multi-task learning

Pan, Yunpeng, Du, Yongping, Wang, Chencheng, Ji, Junzhong

2018

Overview

Background Biomedical semantic indexing is important for information retrieval and many other research fields in bioinformatics. It annotates biomedical citations with Medical Subject Headings. In face of unbalanced category distribution in the training data, sampling methods are difficult to apply for semantic indexing task. Results In this paper, we present a novel deep serial multi-task learning model. The primary task treats the biomedical semantic indexing as a multi-label text classification issue that considers the relations of the labels. The auxiliary task is a regression task that predicts the MeSH number of the citation and provides hints for the network to make it converge faster. The experimental results on the BioASQ-Task5A open dataset show that our model outperforms the state-of-the-art solution “MTI”, proposed by the US National Library of Medicine. Further, it not only achieves the highest precision among all the solutions in BioASQ-Task5A but also has faster convergence speed compared with some naive deep learning methods. Conclusions Rather than parallel in an ordinary multi-task structure, the tasks in our model are serial and tightly coupled. It can achieve satisfied performance without any handcrafted feature.

• Publisher: BioMed Central,BioMed Central Ltd,Springer Nature B.V,BMC
• Subject: Abstracting and Indexing as Topic / Algorithms / Artificial intelligence / Artificial neural networks / Bioinformatics / Biomedical and Life Sciences / Biomedical semantic indexing / Classification / Computational Biology/Bioinformatics / Computer Appl. in Life Sciences / Convergence / Data mining / Deep Learning / Finite element method / Humans / Indexing / Information processing / Information retrieval / International conferences / Life Sciences / Linguistics / Machine learning / Machine translation / Medical research / Medical Subject Headings-MeSH / Microarrays / Multi-label classification / Multi-task learning / National libraries / Natural language processing / Neural networks / Neural Networks (Computer) / Query expansion / Sampling methods / Semantics / State of the art / Subject heading schemes / Word embedding