Filters








120 Hits in 8.6 sec

Wide-scope biomedical named entity recognition and normalization with CRFs, fuzzy matching and character level modeling

Suwisa Kaewphan, Kai Hakala, Niko Miekka, Tapio Salakoski, Filip Ginter
2018 Database: The Journal of Biological Databases and Curation  
Wide-scope biomedical named entity recognition and normalization with CRFs, fuzzy matching and character level modeling.  ...  For normalizing the mentions into unique identifiers we use fuzzy character n-gram matching.  ...  submitted to the shared task (combined), improved CRF model (independent) and the neural character level model (CNN-BiLSTM-CRF) based on the official evaluation script with strict entity span matching  ... 
doi:10.1093/database/bay096 pmid:30239666 pmcid:PMC6146133 fatcat:ucwbwtyftzdvtab7a36v6ayrfa

Analyzing transfer learning impact in biomedical cross-lingual named entity recognition and normalization

Renzo M. Rivera-Zavala, Paloma Martínez
2021 BMC Bioinformatics  
For the entity normalization task, the extended Bi-LSTM-CRF model achieves an F-score of 72.85% and the BERT model achieves 79.97%.  ...  Named Entity Recognition (NER) is the first step for information and knowledge acquisition when we deal with unstructured texts.  ...  Acknowledgements We thank to PharmaCoNER challenge organizers, who provided publicly available training and testing datasets.  ... 
doi:10.1186/s12859-021-04247-9 pmid:34920703 pmcid:PMC8680060 fatcat:dsavlikunvc4zeejhsl74hteo4

Improving Named Entity Recognition for Biomedical and Patent Data Using Bi-LSTM Deep Neural Network Models [chapter]

Farag Saad, Hidir Aras, René Hackl-Sommer
2020 Lecture Notes in Computer Science  
Our deep NN based Bi-LSTM model using word and character level embeddings outperforms CRF and Bi-LSTM using only word level embeddings significantly.  ...  A fundamental step hereby is to find key information (named entities) inside these publications applying Biomedical Named Entities Recognition (BNER).  ...  Due to the fact that a biomedical named entity can exist in different written forms, e.g., "SRC1 ", "SRC 1 ", and "SRC-1 ", performing the exact match of the biomedical named entity in a given text with  ... 
doi:10.1007/978-3-030-51310-8_3 fatcat:d6larpsk45h3bbdxojpdo74phi

A Hybrid Stepwise Approach for De-identifying Person Names in Clinical Documents

Óscar Ferrández, Brett R. South, Shuying Shen, Stéphane M. Meystre
2012 Workshop on Biomedical Natural Language Processing  
or named entity recognition systems.  ...  As a result, our system reached 92.6% F 2measure when de-identifying person names in Veteran's Health Administration clinical notes, and considerably outperformed other existing "out-of-the-box" de-identification  ...  started with the implementation and evaluation of several existing de-identification and Named Entity Recognition (NER) systems recognizing person names.  ... 
dblp:conf/bionlp/FerrandezSSM12 fatcat:pcaji3f75ncelpsrkrpealosx4

Computational Reproducibility of Named Entity Recognition methods in the biomedical domain

Ana García-Serrano, Sebastian Hennig, Andreas Nürnberger
2021 Revista de Procesamiento de Lenguaje Natural (SEPLN)  
The Unsupervised Biomedical Named Entity Recognition framework (UB-NER) is developed, with which the results of the experiments of the three models, five datasets and two NER tasks are presented.  ...  Unsupervised Named Entity Recognition (NER) approaches do not depend on labelled data to function properly but rather on a source of knowledge, in which promising candidates can be looked up to find the  ...  We also want to thank Dina Demner-Fushman and Willie Rogers. The feedback provided by them were really helpful.  ... 
dblp:journals/pdln/Garcia-SerranoH21 fatcat:x5okvymyefcplenbsucb43kspi

Proceedings of the BioCreative V.5 Challenge Evaluation Workshop

Martin Krallinger, Alfonso Valencia
2022 Zenodo  
D+i 2013-2016, funded by ISCIII and ERDF.  ...  Acknowledgment We acknowledge the OpenMinted (654021) and the ELIXIR-EXCELERATE (676559) H2020 projects, and the Encomienda MINETAD-CNIO as part of the Plan for the Advancement of Lan-guage Technology  ...  We perform our experiments using TaggerOne, a recently released system for joint named entity recognition and normalization for various biomedical entities [12] .  ... 
doi:10.5281/zenodo.6519885 fatcat:gzzr6ogkwvfe3eglv6anrzt5s4

Named Entity Recognition and Relation Detection for Biomedical Information Extraction

Nadeesha Perera, Matthias Dehmer, Frank Emmert-Streib
2020 Frontiers in Cell and Developmental Biology  
In this paper, we review practices for Named Entity Recognition (NER) and Relation Detection (RD), allowing, e.g., to identify interactions between proteins and drugs or genes and diseases.  ...  The number of scientific publications in the literature is steadily growing, containing our knowledge in the biomedical, health, and clinical sciences.  ...  For achieving the best results, Bi-LSTM and CRFs models are combined with a word-level and character-level embedding in a structure, as illustrated in Figure 6 (Habibi et al., 2017; Wang et al., 2018a  ... 
doi:10.3389/fcell.2020.00673 pmid:32984300 pmcid:PMC7485218 fatcat:khclwjfykjfi3jktvrbuliwidm

A Concise Survey on Datasets, Tools and Methods for Biomedical Text

R. Johnsi, G. Bharadwaja Kumar, Tulasi Prasad Sariki
2022 International Journal of Applied Engineering Research  
This survey aims to bring out comprehensive tools, technologies, available Biomedical resources, algorithms and challenges faced in Biomedical text mining tasks.  ...  Biomedical text mining aims to retrieve useful information from large data efficiently and convert it into practical usage in a way of diagnosing symptoms, prevention, and treatment of diseases.  ...  Biomedical Named Entity Recognition task Biomedical Named Entity Recognition (Bio-NER) is used to automatically recognize Biomedical entities (e.g., chemicals, diseases and Proteins) in given texts.  ... 
doi:10.37622/ijaer/17.3.2022.200-217 fatcat:2cw7f572rjfqvbnbrpq7gc75ue

Named Entity Recognition and Classification on Historical Documents: A Survey [article]

Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes, Matteo Romanello, Antoine Doucet
2021 arXiv   pre-print
Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical and noisy inputs.  ...  Among semantic indexing opportunities, the recognition and classification of named entities are in great demand among humanities scholars.  ...  ACKNOWLEDGMENTS The work of Maud Ehrmann and Matteo Romanello was supported by the Swiss National Science Foundation under the grants number CR-SII5_173719 (Impresso -Media Monitoring of the Past) and  ... 
arXiv:2109.11406v1 fatcat:zbwoybklk5bjrlf2b67qm6t7e4

BioCreative II Workshop Proceedings

Lynette, Martin, Alfonso
2007 Zenodo  
Conditional Random Fields and n-Gram Language Models for Gene Mention Recognition 85 Tackling the BioCreative2 Gene Mention task with Conditional Random Fields and Syntactic Parsing 89 Named Entity Recognition  ...  : gene mention normalization with background knowledge 145 Context-Aware Mapping of Gene Names using Trigrams 149 ProMiner: Recognition of Human Gene and Protei [...]  ...  The hierarchical pattern matching algorithm gives higher flexibility than traditional rule-based approach and maintains high precision by using most specific pattern level.  ... 
doi:10.5281/zenodo.4274543 fatcat:3sa3fvgngffjrblxzgswof42tq

Recent progress in automatically extracting information from the pharmacogenomic literature

Yael Garten, Adrien Coulet, Russ B Altman
2010 Pharmacogenomics (London)  
Acknowledgements The authors would like to thank Connie M Oshiro for comments on the manuscript and Nicholas P Tatonetti for useful discussions and assistance creating the figures.  ...  reported that up to 79% of failures in gene name recognition could be caused by character-level and word-level variations [44] .  ...  These approaches develop a statistical model for entity recognition.  ... 
doi:10.2217/pgs.10.136 pmid:21047206 pmcid:PMC3035632 fatcat:7g3jwc4hjfetbb5phmzstzhjeu

Applications of Natural Language Processing in Biodiversity Science

Anne E. Thessen, Hong Cui, Dmitry Mozzherin
2012 Advances in Bioinformatics  
Many tools exist for biological information extraction (cellular processes, taxonomic names, and morphological characters), but none have been applied life wide and most still require testing and development  ...  Progress has been made in developing algorithms for automated annotation of taxonomic text, identification of taxonomic names in text, and extraction of morphological character information from taxonomic  ...  Holly Bowers, and Mr. Nathan Wilson for thoughtful comments on an early version of this manuscript and productive discussion.  ... 
doi:10.1155/2012/391574 pmid:22685456 pmcid:PMC3364545 fatcat:qsqdapr7bvdkbaro2e4kkg3v2q

Proceedings of the second biocreative challenge evaluation workshop

Lynette Hirschman, Martin Krallinger, Alfonso Valencia
2007 Zenodo  
of the AIIA-GMT system to the BioCreative III Gene Normalization data.  ...  Acknowledgements The MyMiner project was supported by, MyoRes European Network of Excellence dedicated to study normal and aberrant muscle development function and repair and the French Association against  ...  NERsuite is a toolkit for named entity recognition based on Conditional Random Fields (CRFs).  ... 
doi:10.5281/zenodo.6519852 fatcat:k6q4vrkd65hbthlvwnhy2ufiey

Automatic negation detection in narrative pathology reports

Ying Ou, Jon Patrick
2015 Artificial Intelligence in Medicine  
Specifically, the medical entity recognition system used conditional random fields (CRF) learners.  ...  The CRF-based models were able to capture a significant portion of the entity boundaries by iii using contextual information.  ...  Named entity recognition (NER) aims at identifying specific words or phrases ("entities") and categorizing them.  ... 
doi:10.1016/j.artmed.2015.03.001 pmid:25990897 fatcat:yrijkncnsvht7lonmaqt7uyya4

Large Language Models are Zero-Shot Clinical Information Extractors [article]

Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, David Sontag
2022 arXiv   pre-print
., "safety checks" that ensure the language model outputs faithfully match the input data), and that the common patterns across tasks make resolvers lightweight and easy to create.  ...  ., 2014) with labels for new tasks. On the clinical extraction tasks we studied, the GPT-3 + resolver systems significantly outperform existing zero- and few-shot baselines.  ...  Thanks to NVIDIA Corporation for their donation of two NVIDIA A100 GPUs, and to OpenAI for providing quota to access their models.  ... 
arXiv:2205.12689v1 fatcat:6ypput4f4rfunbdqsvq5ske2si
« Previous Showing results 1 — 15 out of 120 results