<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Wang K</submitter><funding>NHLBI NIH HHS</funding><funding>NIMH NIH HHS</funding><funding>Biotechnology and Biological Sciences Research Council</funding><funding>Engineering and Physical Sciences Research Council</funding><pagination>38</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC8528865</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>7(1)</volume><pubmed_abstract>Machine reading (MR) is essential for unlocking valuable knowledge contained in millions of existing biomedical documents. Over the last two decades&lt;sup>1,2&lt;/sup>, the most dramatic advances in MR have followed in the wake of critical corpus development&lt;sup>3&lt;/sup>. Large, well-annotated corpora have been associated with punctuated advances in MR methodology and automated knowledge extraction systems in the same way that ImageNet&lt;sup>4&lt;/sup> was fundamental for developing machine vision techniques. This study contributes six components to an advanced, named entity analysis tool for biomedicine: (a) a new, Named Entity Recognition Ontology (NERO) developed specifically for describing textual entities in biomedical texts, which accounts for diverse levels of ambiguity, bridging the scientifi</pubmed_abstract><journal>NPJ systems biology and applications</journal><pubmed_title>NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding.</pubmed_title><pmcid>PMC8528865</pmcid><funding_grant_id>EP/S014128/1</funding_grant_id><funding_grant_id>EP/R022925/2</funding_grant_id><funding_grant_id>EP/R022925/1</funding_grant_id><funding_grant_id>GR/S47656/01</funding_grant_id><funding_grant_id>EP/K030469/1</funding_grant_id><funding_grant_id>BB/F008228/1</funding_grant_id><funding_grant_id>EP/R022941/1</funding_grant_id><funding_grant_id>U01 HL108634</funding_grant_id><funding_grant_id>BEP17028</funding_grant_id><funding_grant_id>BB/G000662/1</funding_grant_id><funding_grant_id>EP/K030582/1</funding_grant_id><funding_grant_id>BB/D006503/1</funding_grant_id><funding_grant_id>R01 HL122712</funding_grant_id><funding_grant_id>BB/E018025/1</funding_grant_id><funding_grant_id>EP/M015688/1</funding_grant_id><funding_grant_id>P50 MH094267</funding_grant_id><funding_grant_id>EP/W004801/1</funding_grant_id><funding_grant_id>1441239</funding_grant_id><funding_grant_id>K12 HL143959</funding_grant_id><funding_grant_id>BB/D00425X/1</funding_grant_id><funding_grant_id>EP/M015661/1</funding_grant_id><pubmed_authors>Alachram H</pubmed_authors><pubmed_authors>Christopoulou F</pubmed_authors><pubmed_authors>Matthew J</pubmed_authors><pubmed_authors>Stevens R</pubmed_authors><pubmed_authors>Chambers B</pubmed_authors><pubmed_authors>Schoene AM</pubmed_authors><pubmed_authors>Wang K</pubmed_authors><pubmed_authors>Sheng E</pubmed_authors><pubmed_authors>Ananiadou S</pubmed_authors><pubmed_authors>Hermjakob U</pubmed_authors><pubmed_authors>Galstyan A</pubmed_authors><pubmed_authors>Garg S</pubmed_authors><pubmed_authors>Rzhetsky A</pubmed_authors><pubmed_authors>Evans JA</pubmed_authors><pubmed_authors>King R</pubmed_authors><pubmed_authors>Pan W</pubmed_authors><pubmed_authors>Soldatova L</pubmed_authors><pubmed_authors>Li M</pubmed_authors><pubmed_authors>Beißbarth T</pubmed_authors><pubmed_authors>Marcu D</pubmed_authors><pubmed_authors>Li Y</pubmed_authors><pubmed_authors>Wingender E</pubmed_authors><pubmed_authors>Gao X</pubmed_authors><pubmed_authors>Ambite JL</pubmed_authors><pubmed_authors>Khomtchouk BB</pubmed_authors></additional><is_claimable>false</is_claimable><name>NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding.</name><description>Machine reading (MR) is essential for unlocking valuable knowledge contained in millions of existing biomedical documents. Over the last two decades&lt;sup>1,2&lt;/sup>, the most dramatic advances in MR have followed in the wake of critical corpus development&lt;sup>3&lt;/sup>. Large, well-annotated corpora have been associated with punctuated advances in MR methodology and automated knowledge extraction systems in the same way that ImageNet&lt;sup>4&lt;/sup> was fundamental for developing machine vision techniques. This study contributes six components to an advanced, named entity analysis tool for biomedicine: (a) a new, Named Entity Recognition Ontology (NERO) developed specifically for describing textual entities in biomedical texts, which accounts for diverse levels of ambiguity, bridging the scientifi</description><dates><release>2021-01-01T00:00:00Z</release><publication>2021 Oct</publication><modification>2026-05-07T22:20:39.799Z</modification><creation>2025-02-19T03:53:08.14Z</creation></dates><accession>S-EPMC8528865</accession><cross_references><pubmed>34671039</pubmed><doi>10.1038/s41540-021-00200-x</doi></cross_references></HashMap>