Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition.
Background: This work deals with Natural Language Processing applied to the clinical domain. Specifically, the work deals with a Medical Entity Recognition (MER) on Electronic Health Records (EHRs). Developing a MER system entailed heavy data preprocessing and feature engineering until Deep Neural N...
| Published in: | International Journal of Medical Informatics Vol. 129; pp. 100 - 107 |
|---|---|
| Main Authors: | , , , , |
| Format: | research Journal Article |
| Published: |
Elsevier B.V.
Sep2019
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=138293945&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 138293945 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 13865056 JR4 jtl: International Journal of Medical Informatics issn: 13865056 maglogo: N pubinfo: dt: Sep2019 vid: 129 pid: 467 pub: Elsevier B.V. place: New York, New York artinfo: ui: 138293945 138293945 NLM31445243 138293945 10.1016/j.ijmedinf.2019.05.022 NLM31445243 138293945 ppf: 100 ppct: 7 formats: tig: atl: Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition. aug: au: Casillas, Arantza Ezeiza, Nerea Goenaga, Iakes Pérez, Alicia Soto, Xabier affil: IXA Group, University of the Basque Country (UPV-EHU), Manuel Lardizabal 1, 20080 Donostia, Spain sug: subj: Natural Language Processing Algorithms Neural Networks (Computer) Subject Headings Semantics Validation Studies Comparative Studies Evaluation Research Multicenter Studies Ferrans and Powers Quality of Life Index Impact of Events Scale Questionnaires Scales Short Portable Mental Status Questionnaire ab: Background: This work deals with Natural Language Processing applied to the clinical domain. Specifically, the work deals with a Medical Entity Recognition (MER) on Electronic Health Records (EHRs). Developing a MER system entailed heavy data preprocessing and feature engineering until Deep Neural Networks (DNNs) emerged. However, the quality of the word representations in terms of embedded layers is still an important issue for the inference of the DNNs.Goal: The main goal of this work is to develop a robust MER system adapting general-purpose DNNs to cope with the high lexical variability shown in EHRs. In addition, given that EHRs tend to be scarce when there are out-domain corpora available, the aim is to assess the impact of the word representations on the performance of the MER as we move to other domains. In this line, exhaustive experimentation varying information generation methods and network parameters are crucial.Methods: We adapted a general purpose sequential tagger based on Bidirectional Long-Short Term Memory cells and Conditional Random Fields (CRFs) in order to make it tolerant to high lexical variability and a limited amount of corpora. To this end, we incorporated part of speech (POS) and semantic-tag embedding layers to the word representations.Results: One of the strengths of this work is the exhaustive evaluation of dense word representations obtained varying not only the domain and genre but also the learning algorithms and their parameter settings. With the proposed method, we attained an error reduction of 1.71 (5.7%) compared to the state-of-the-art even that no preprocessing or feature engineering was used.Conclusions: Our results indicate that dense representations built taking word order into account leverage the entity extraction system. Besides, we found that using a medical corpus (not necessarily EHRs) to infer the representations improves the performance, even if it does not correspond to the same genre. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|