About: On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts
Creator	Alimova, Ilseyar Miftahutdinov, Zulfat Tutubalina, Elena
Source	PMC
abstract	Although deep neural networks yield state-of-the-art performance in biomedical named entity recognition (bioNER), much research shares one limitation: models are usually trained and evaluated on English texts from a single domain. In this work, we present a fine-grained evaluation intended to understand the efficiency of multilingual BERT-based models for bioNER of drug and disease mentions across two domains in two languages, namely clinical data and user-generated texts on drug therapy in English and Russian. We investigate the role of transfer learning (TL) strategies between four corpora to reduce the number of examples that have to be manually annotated. Evaluation results demonstrate that multi-BERT shows the best transfer capabilities in the zero-shot setting when training and test sets are either in the same language or in the same domain. TL reduces the amount of labeled data needed to achieve high performance on three out of four corpora: pretrained models reach 98–99% of the full dataset performance on both types of entities after training on 10–25% of sentences. We demonstrate that pretraining on data with one or both types of transfer can be effective.
has issue date	2020-03-24(xsd:dateTime)
bibo:doi	10.1007/978-3-030-45442-5_35
has license	no-cc
sha1sum (hex)	e06f6d79b57ddf9e8fecc0b24a8e3045ea66ad9a
schema:url	https://doi.org/10.1007/978-3-030-45442-5_35
resource representing a document's title	On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts
has PubMed Central identifier	PMC7148079
schema:publication	Advances in Information Retrieval
resource representing a document's body	covid:e06f6d79b57ddf9e8fecc0b24a8e3045ea66ad9a#body_text
is schema:about of	named entity 'strategies' named entity 'reduces' named entity 'evaluation' named entity 'intended' named entity 'annotated' named entity 'EITHER' named entity 'CLINICAL DATA' named entity 'STRATEGIES' named entity 'TRANSFER LEARNING' named entity 'YIELD' named entity 'PERFORMANCE' named entity 'DATASET' named entity 'dataset' named entity 'single' named entity 'corpora' named entity 'performance' named entity 'texts' named entity 'domains' named entity 'zero-shot' named entity 'transfer learning' named entity 'named entity recognition' named entity 'Interlingual' named entity 'EHRs' named entity 'multilingual' named entity 'adverse drug reactions' named entity 'NER' named entity 'UGTs' named entity 'neural networks' named entity 'word2vec' named entity 'Lipitor' named entity 'clinical trials' named entity 'transfer learning' named entity 'UGTs' named entity 'Kazan Federal University' named entity 'UGTs' named entity 'named entity recognition' named entity 'EHRs' named entity 'sample size' named entity 'language models' named entity 'detection of drugs' named entity 'transfer learning' named entity 'learning rate' named entity 'social media' named entity 'Russian National Corpus' named entity 'UGTs' named entity 'multi-disciplinary' named entity 'training set' named entity 'softmax layer' named entity 'Multilingual' named entity 'Transfer learning' named entity 'Lipitor' named entity 'NER' named entity 'NER' named entity 'NVIDIA' named entity 'zero-shot' named entity 'zero-shot' named entity 'NER' named entity 'multilingual' named entity 'EHRs' named entity 'UGTs' named entity 'word embeddings' named entity 'EHR' named entity 'training set' named entity 'NER' named entity 'overfitting' named entity 'social media' named entity 'Diclofenac' named entity 'training set' named entity 'eHealth' named entity 'statistically significant' named entity 'detection of drugs' named entity 'training set' named entity 'UGTs' named entity 'EHR' named entity 'multilingual' named entity 'hidden units' named entity 'LSTM' named entity 'multilingual' named entity 'electronic health records' named entity 'word2vec' named entity 'random sampling'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software