Design, implementation, and operation of a rapid, robust named entity recognition web service

Research output: Contribution to journalJournal articleResearchpeer-review

Standard

Design, implementation, and operation of a rapid, robust named entity recognition web service. / Pletscher-Frankild, Sune; Jensen, Lars Juhl.

In: Journal of Cheminformatics, Vol. 11, 19, 2019.

Research output: Contribution to journalJournal articleResearchpeer-review

Harvard

Pletscher-Frankild, S & Jensen, LJ 2019, 'Design, implementation, and operation of a rapid, robust named entity recognition web service', Journal of Cheminformatics, vol. 11, 19. https://doi.org/10.1186/s13321-019-0344-9

APA

Pletscher-Frankild, S., & Jensen, L. J. (2019). Design, implementation, and operation of a rapid, robust named entity recognition web service. Journal of Cheminformatics, 11, [19]. https://doi.org/10.1186/s13321-019-0344-9

Vancouver

Pletscher-Frankild S, Jensen LJ. Design, implementation, and operation of a rapid, robust named entity recognition web service. Journal of Cheminformatics. 2019;11. 19. https://doi.org/10.1186/s13321-019-0344-9

Author

Pletscher-Frankild, Sune ; Jensen, Lars Juhl. / Design, implementation, and operation of a rapid, robust named entity recognition web service. In: Journal of Cheminformatics. 2019 ; Vol. 11.

Bibtex

@article{848483bdba1d43a886331ab22784acec,
title = "Design, implementation, and operation of a rapid, robust named entity recognition web service",
abstract = "Most BioCreative tasks to date have focused on assessing the quality of text-mining annotations in terms of precision and recall. Interoperability, speed, and stability are, however, other important factors to consider for practical applications of text mining. For about a decade, we have run named entity recognition (NER) web services, which are designed to be efficient, implemented using a multi-threaded queueing system to robustly handle many simultaneous requests, and hosted at a supercomputer facility. To participate in this new task, we extended the existing NER tagging service with support for the BeCalm API. The tagger suffered no downtime during the challenge and, as in earlier tests, proved to be highly efficient, consistently processing requests of 5000 abstracts in less than half a minute. In fact, the majority of this time was spent not on the NER task but rather on retrieving the document texts from the challenge servers. The latter was found to be the main bottleneck even when hosting a copy of the tagging service on a Raspberry Pi 3, showing that local document storage or caching would be desirable features to include in future revisions of the API standard.",
author = "Sune Pletscher-Frankild and Jensen, {Lars Juhl}",
year = "2019",
doi = "10.1186/s13321-019-0344-9",
language = "English",
volume = "11",
journal = "Journal of Cheminformatics",
issn = "1758-2946",
publisher = "Springer International Publishing",

}

RIS

TY - JOUR

T1 - Design, implementation, and operation of a rapid, robust named entity recognition web service

AU - Pletscher-Frankild, Sune

AU - Jensen, Lars Juhl

PY - 2019

Y1 - 2019

N2 - Most BioCreative tasks to date have focused on assessing the quality of text-mining annotations in terms of precision and recall. Interoperability, speed, and stability are, however, other important factors to consider for practical applications of text mining. For about a decade, we have run named entity recognition (NER) web services, which are designed to be efficient, implemented using a multi-threaded queueing system to robustly handle many simultaneous requests, and hosted at a supercomputer facility. To participate in this new task, we extended the existing NER tagging service with support for the BeCalm API. The tagger suffered no downtime during the challenge and, as in earlier tests, proved to be highly efficient, consistently processing requests of 5000 abstracts in less than half a minute. In fact, the majority of this time was spent not on the NER task but rather on retrieving the document texts from the challenge servers. The latter was found to be the main bottleneck even when hosting a copy of the tagging service on a Raspberry Pi 3, showing that local document storage or caching would be desirable features to include in future revisions of the API standard.

AB - Most BioCreative tasks to date have focused on assessing the quality of text-mining annotations in terms of precision and recall. Interoperability, speed, and stability are, however, other important factors to consider for practical applications of text mining. For about a decade, we have run named entity recognition (NER) web services, which are designed to be efficient, implemented using a multi-threaded queueing system to robustly handle many simultaneous requests, and hosted at a supercomputer facility. To participate in this new task, we extended the existing NER tagging service with support for the BeCalm API. The tagger suffered no downtime during the challenge and, as in earlier tests, proved to be highly efficient, consistently processing requests of 5000 abstracts in less than half a minute. In fact, the majority of this time was spent not on the NER task but rather on retrieving the document texts from the challenge servers. The latter was found to be the main bottleneck even when hosting a copy of the tagging service on a Raspberry Pi 3, showing that local document storage or caching would be desirable features to include in future revisions of the API standard.

U2 - 10.1186/s13321-019-0344-9

DO - 10.1186/s13321-019-0344-9

M3 - Journal article

C2 - 30850898

VL - 11

JO - Journal of Cheminformatics

JF - Journal of Cheminformatics

SN - 1758-2946

M1 - 19

ER -

ID: 214827358