Evaluating sentence representations for biomedical text: Methods and experimental results.
Text representations ar one of the main inputs to various Natural Language Processing (NLP) methods. Given the fast developmental pace of new sentence embedding methods, we argue that there is a need for a unified methodology to assess these different techniques in the biomedical domain. This work i...
| Publicado en: | Journal of Biomedical Informatics Vol. 104 |
|---|---|
| Autores principales: | , |
| Formato: | Journal Article |
| Publicado: |
Academic Press Inc.
Apr2020
|
| 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=142561001&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 142561001 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 15320464 OMB jtl: Journal of Biomedical Informatics issn: 15320464 maglogo: N pubinfo: dt: Apr2020 vid: 104 pid: 735 pub: Academic Press Inc. place: Burlington, Massachusetts artinfo: ui: 142561001 142561001 NLM32147441 10.1016/j.jbi.2020.103396 NLM32147441 142561001 ppct: 1 formats: tig: atl: Evaluating sentence representations for biomedical text: Methods and experimental results. aug: au: Tawfik, Noha S. Spruit, Marco R. affil: Computer Engineering Department, College of Engineering, Arab Academy for Science, Technology, and Maritime Transport (AAST), 1029 Alexandria, Egypt sug: subj: Language Natural Language Processing Software Semantics Clinical Assessment Tools Scales ab: Text representations ar one of the main inputs to various Natural Language Processing (NLP) methods. Given the fast developmental pace of new sentence embedding methods, we argue that there is a need for a unified methodology to assess these different techniques in the biomedical domain. This work introduces a comprehensive evaluation of novel methods across ten medical classification tasks. The tasks cover a variety of BioNLP problems such as semantic similarity, question answering, citation sentiment analysis and others with binary and multi-class datasets. Our goal is to assess the transferability of different sentence representation schemes to the medical and clinical domain. Our analysis shows that embeddings based on Language Models which account for the context-dependent nature of words, usually outperform others in terms of performance. Nonetheless, there is no single embedding model that perfectly represents biomedical and clinical texts with consistent performance across all tasks. This illustrates the need for a more suitable bio-encoder. Our MedSentEval source code, pre-trained embeddings and examples have been made available on GitHub. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|