Conditional Random Fields for Biomedical Named Entity Recognition Revisited

Entity Recognition ◽

Biomedical Domain ◽

Minimal Set ◽

Named Entities ◽

Named Entity ◽

Biomedical Texts ◽

Abstract Named Entity Recognition (NER) is a key task which automatically extracts Named Entities (NE) from the text. Names of persons, places, date and time are examples of NEs. We are applying Conditional Random Fields (CRFs) for NER in biomedical domain. Examples of NEs in biomedical texts are gene, proteins. We used a minimal set of features to train CRF algorithm and obtained a good results for biomedical texts.

NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding

npj Systems Biology and Applications ◽

10.1038/s41540-021-00200-x ◽

2021 ◽

Vol 7 (1) ◽

Author(s):

Kanix Wang ◽

Robert Stevens ◽

Halima Alachram ◽

Yu Li ◽

Larisa Soldatova ◽

...

Keyword(s):

Entity Recognition ◽

Analysis Tool ◽

Automated Extraction ◽

Named Entities ◽

Named Entity ◽

Automated Knowledge ◽

Biomedical Texts ◽

Machine Reading ◽

AbstractMachine reading (MR) is essential for unlocking valuable knowledge contained in millions of existing biomedical documents. Over the last two decades1,2, the most dramatic advances in MR have followed in the wake of critical corpus development3. Large, well-annotated corpora have been associated with punctuated advances in MR methodology and automated knowledge extraction systems in the same way that ImageNet4 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 scientific sublanguages of molecular biology, genetics, biochemistry, and medicine; (b) detailed guidelines for human experts annotating hundreds of named entity classes; (c) pictographs for all named entities, to simplify the burden of annotation for curators; (d) an original, annotated corpus comprising 35,865 sentences, which encapsulate 190,679 named entities and 43,438 events connecting two or more entities; (e) validated, off-the-shelf, named entity recognition (NER) automated extraction, and; (f) embedding models that demonstrate the promise of biomedical associations embedded within this corpus.

International Conference on Computer Technology and Development, 3rd (ICCTD 2011) ◽

Biomedical Named Entity Recognition Using Second-Order Conditional Random Fields

10.1115/1.859919.paper198 ◽

2011 ◽

pp. 1213-1217

Keyword(s):

Random Fields ◽

Second Order ◽

Entity Recognition ◽

Named Entity ◽

A conditional random fields approach to biomedical named entity recognition

Journal of Electronics (China) ◽

10.1007/s11767-006-0255-6 ◽

2007 ◽

Vol 24 (6) ◽

pp. 838-844 ◽

Cited By ~ 7

Author(s):

Haochang Wang ◽

Tiejun Zhao ◽

Sheng Li ◽

Hao Yu

Keyword(s):

Random Fields ◽

Entity Recognition ◽

Named Entity ◽

Biomedical named entity recognition using conditional random fields and rich feature sets

10.3115/1567594.1567618 ◽

2004 ◽

Cited By ~ 174

Author(s):

Burr Settles

Keyword(s):

Random Fields ◽

Entity Recognition ◽

Feature Sets ◽

Named Entity ◽

Machine-learning methods for text named entity recognition

PROBLEMS IN PROGRAMMING ◽

10.15407/pp2016.02-03.150 ◽

2016 ◽

pp. 150-157

Author(s):

O.O. Marchenko ◽

Keyword(s):

Machine Learning ◽

Random Fields ◽

Entity Recognition ◽

Learning Methods ◽

Named Entities ◽

Named Entity ◽

Machine Learning Methods ◽

Multi Classification

The article describes machine learning methods for the named entity recognition. To build named entity classifiers two basic models of machine learning, The Naїve Bayes and Conditional Random Fields, were used. A model for multi-classification of named entities using Error Correcting Output Codes was also researched. The paper describes a method for classifiers' training and the results of test experiments. Conditional Random Fields overcome other models in precision and recall evaluations.

NERO: A Biomedical Named-entity (Recognition) Ontology with a Large, Annotated Corpus Reveals Meaningful Associations Through Text Embedding

10.1101/2020.11.05.368969 ◽

2020 ◽

Author(s):

Kanix Wang ◽

Robert Stevens ◽

Halima Alachram ◽

Yu Li ◽

Larisa Soldatova ◽

...

Keyword(s):

Entity Recognition ◽

Analysis Tool ◽

Automated Extraction ◽

Named Entities ◽

Named Entity ◽

Automated Knowledge ◽

Biomedical Texts ◽

Machine Reading ◽

Machine reading is essential for unlocking valuable knowledge contained in the millions of existing biomedical documents. Over the last two decades 1,2, the most dramatic advances in machine-reading have followed in the wake of critical corpus development3. Large, well-annotated corpora have been associated with punctuated advances in machine reading methodology and automated knowledge extraction systems in the same way that ImageNet 4 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 entities in biomedical texts, which accounts for diverse levels of ambiguity, bridging the scientific sublanguages of molecular biology, genetics, biochemistry, and medicine; (b) detailed guidelines for human experts annotating hundreds of named-entity classes; (c) pictographs for all named entities, to simplify the burden of annotation for curators; (d) an original, annotated corpus comprising 35,865 sentences, which encapsulate 190,679 named entities and 43,438 events connecting two or more entities; (e) validated, off-the-shelf, named-entity recognition automated extraction, and; (f) embedding models that demonstrate the promise of biomedical associations embedded within this corpus.