Character-level neural network for biomedical named entity recognition.
Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of f...
| Publicado en: | Journal of Biomedical Informatics Vol. 70; pp. 85 - 92 |
|---|---|
| Autor principal: | |
| Formato: | research Journal Article |
| Publicado: |
Academic Press Inc.
Jun2017
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=123269770&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 123269770 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 15320464 OMB jtl: Journal of Biomedical Informatics issn: 15320464 maglogo: N pubinfo: dt: Jun2017 vid: 70 pid: 735 pub: Academic Press Inc. place: Burlington, Massachusetts artinfo: ui: 123269770 123269770 NLM28502909 123269770 10.1016/j.jbi.2017.05.002 NLM28502909 123269770 ppf: 85 ppct: 7 formats: tig: atl: Character-level neural network for biomedical named entity recognition. aug: au: Gridach, Mourad affil: High Institute of Technology, Ibn Zohr University, Agadir, Morocco sug: subj: Natural Language Processing Neural Networks (Computer) Proteins Genes Algorithms ab: Biomedical named entity recognition (BNER), which extracts important named entities such as genes and proteins, is a challenging task in automated systems that mine knowledge in biomedical texts. The previous state-of-the-art systems required large amounts of task-specific knowledge in the form of feature engineering, lexicons and data pre-processing to achieve high performance. In this paper, we introduce a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks. We evaluate our system on two datasets: JNLPBA corpus and the BioCreAtIvE II Gene Mention (GM) corpus. We obtained state-of-the-art performance by outperforming the previous systems. To the best of our knowledge, we are the first to investigate the combination of deep neural networks, CRF, word embeddings and character-level representation in recognizing biomedical named entities. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|