Ontology type: schema:ScholarlyArticle Open Access: True
2018-12
AUTHORSIlia Korvigo, Maxim Holmatov, Anatolii Zaikovskii, Mikhail Skoblov
ABSTRACTChemical named entity recognition (NER) is an active field of research in biomedical natural language processing. To facilitate the development of new and superior chemical NER systems, BioCreative released the CHEMDNER corpus, an extensive dataset of diverse manually annotated chemical entities. Most of the systems trained on the corpus rely on complicated hand-crafted rules or curated databases for data preprocessing, feature extraction and output post-processing, though modern machine learning algorithms, such as deep neural networks, can automatically design the rules with little to none human intervention. Here we explored this approach by experimenting with various deep learning architectures for targeted tokenisation and named entity recognition. Our final model, based on a combination of convolutional and stateful recurrent neural networks with attention-like loops and hybrid word- and character-level embeddings, reaches near human-level performance on the testing dataset with no manually asserted rules. To make our model easily accessible for standalone use and integration in third-party software, we've developed a Python package with a minimalistic user interface. More... »
PAGES28
http://scigraph.springernature.com/pub.10.1186/s13321-018-0280-0
DOIhttp://dx.doi.org/10.1186/s13321-018-0280-0
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1104161542
PUBMEDhttps://www.ncbi.nlm.nih.gov/pubmed/29796778
JSON-LD is the canonical representation for SciGraph data.
TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT
[
{
"@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json",
"about": [
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Information and Computing Sciences",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "ITMO University",
"id": "https://www.grid.ac/institutes/grid.35915.3b",
"name": [
"Laboratory of Functional Analysis of the Genome, Moscow Institute of Physics and Technology, Moscow, Russia",
"All-Russia Institute for Agricultural Microbiology, St. Petersburg, Russia",
"ITMO University, St. Petersburg, Russia"
],
"type": "Organization"
},
"familyName": "Korvigo",
"givenName": "Ilia",
"id": "sg:person.01031347547.78",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01031347547.78"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Institute of Oncology NN Petrov",
"id": "https://www.grid.ac/institutes/grid.465337.0",
"name": [
"St. Petersburg State Pediatric Medical University, St. Petersburg, Russia",
"N.N. Petrov Institute of Oncology, Department of Tumor Biology, St. Petersburg, Russia"
],
"type": "Organization"
},
"familyName": "Holmatov",
"givenName": "Maxim",
"id": "sg:person.014616536340.61",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014616536340.61"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Saint Petersburg State University",
"id": "https://www.grid.ac/institutes/grid.15447.33",
"name": [
"St. Petersburg State University, St. Petersburg, Russia"
],
"type": "Organization"
},
"familyName": "Zaikovskii",
"givenName": "Anatolii",
"id": "sg:person.012116374366.79",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012116374366.79"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Research Centre for Medical Genetics",
"id": "https://www.grid.ac/institutes/grid.415876.9",
"name": [
"Laboratory of Functional Analysis of the Genome, Moscow Institute of Physics and Technology, Moscow, Russia",
"School of Biomedicine, Far Eastern Federal University, Vladivostok, Russia",
"Laboratory of Functional Genomics, Research Centre for Medical Genetics, Moscow, Russia"
],
"type": "Organization"
},
"familyName": "Skoblov",
"givenName": "Mikhail",
"id": "sg:person.0705736657.47",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0705736657.47"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s5",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1000980620",
"https://doi.org/10.1186/1758-2946-7-s1-s5"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10107-014-0839-0",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1001014149",
"https://doi.org/10.1007/s10107-014-0839-0"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s12",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1003627256",
"https://doi.org/10.1186/1758-2946-7-s1-s12"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s7",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1005695583",
"https://doi.org/10.1186/1758-2946-7-s1-s7"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1830483.1830503",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1006856667"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s8",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1008569362",
"https://doi.org/10.1186/1758-2946-7-s1-s8"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1093/bioinformatics/bts183",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1009604079"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s10",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1013266346",
"https://doi.org/10.1186/1758-2946-7-s1-s10"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s11",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1017378957",
"https://doi.org/10.1186/1758-2946-7-s1-s11"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s9",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1028825212",
"https://doi.org/10.1186/1758-2946-7-s1-s9"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s1",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1040426793",
"https://doi.org/10.1186/1758-2946-7-s1-s1"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s4",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1041223315",
"https://doi.org/10.1186/1758-2946-7-s1-s4"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-94-017-2390-9_10",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1043560139",
"https://doi.org/10.1007/978-94-017-2390-9_10"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s3",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1043621969",
"https://doi.org/10.1186/1758-2946-7-s1-s3"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s14",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1043905339",
"https://doi.org/10.1186/1758-2946-7-s1-s14"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1186/1758-2946-7-s1-s2",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1048097290",
"https://doi.org/10.1186/1758-2946-7-s1-s2"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1021/acs.jcim.6b00207",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1055098359"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2015.7298761",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095305380"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.18653/v1/d16-1157",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1098653560"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.18653/v1/d15-1176",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099106154"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.3115/v1/d14-1162",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099110523"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.3115/v1/d14-1162",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099110523"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1093/bioinformatics/btx815",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099890718"
],
"type": "CreativeWork"
}
],
"datePublished": "2018-12",
"datePublishedReg": "2018-12-01",
"description": "Chemical named entity recognition (NER) is an active field of research in biomedical natural language processing. To facilitate the development of new and superior chemical NER systems, BioCreative released the CHEMDNER corpus, an extensive dataset of diverse manually annotated chemical entities. Most of the systems trained on the corpus rely on complicated hand-crafted rules or curated databases for data preprocessing, feature extraction and output post-processing, though modern machine learning algorithms, such as deep neural networks, can automatically design the rules with little to none human intervention. Here we explored this approach by experimenting with various deep learning architectures for targeted tokenisation and named entity recognition. Our final model, based on a combination of convolutional and stateful recurrent neural networks with attention-like loops and hybrid word- and character-level embeddings, reaches near human-level performance on the testing dataset with no manually asserted rules. To make our model easily accessible for standalone use and integration in third-party software, we've developed a Python package with a minimalistic user interface.",
"genre": "research_article",
"id": "sg:pub.10.1186/s13321-018-0280-0",
"inLanguage": [
"en"
],
"isAccessibleForFree": true,
"isFundedItemOf": [
{
"id": "sg:grant.4895952",
"type": "MonetaryGrant"
}
],
"isPartOf": [
{
"id": "sg:journal.1042252",
"issn": [
"1758-2946"
],
"name": "Journal of Cheminformatics",
"type": "Periodical"
},
{
"issueNumber": "1",
"type": "PublicationIssue"
},
{
"type": "PublicationVolume",
"volumeNumber": "10"
}
],
"name": "Putting hands to rest: efficient deep CNN-RNN architecture for chemical named entity recognition with no hand-crafted rules",
"pagination": "28",
"productId": [
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"cdb7f5e20ab698f7e7344ceb7f5415327e250f4a98801e60bdd670c9b5a633ca"
]
},
{
"name": "pubmed_id",
"type": "PropertyValue",
"value": [
"29796778"
]
},
{
"name": "nlm_unique_id",
"type": "PropertyValue",
"value": [
"101516718"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1186/s13321-018-0280-0"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1104161542"
]
}
],
"sameAs": [
"https://doi.org/10.1186/s13321-018-0280-0",
"https://app.dimensions.ai/details/publication/pub.1104161542"
],
"sdDataset": "articles",
"sdDatePublished": "2019-04-10T16:01",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8664_00000572.jsonl",
"type": "ScholarlyArticle",
"url": "https://link.springer.com/10.1186%2Fs13321-018-0280-0"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
JSON-LD is a popular format for linked data which is fully compatible with JSON.
curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s13321-018-0280-0'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13321-018-0280-0'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13321-018-0280-0'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13321-018-0280-0'
This table displays all metadata directly associated to this object as RDF triples.
185 TRIPLES
21 PREDICATES
51 URIs
21 LITERALS
9 BLANK NODES