2013
DOI: 10.1093/database/bat020
|View full text |Cite
|
Sign up to set email alerts
|

Preliminary evaluation of the CellFinder literature curation pipeline for gene expression in kidney cells and anatomical parts

Abstract: Biomedical literature curation is the process of automatically and/or manually deriving knowledge from scientific publications and recording it into specialized databases for structured delivery to users. It is a slow, error-prone, complex, costly and, yet, highly important task. Previous experiences have proven that text mining can assist in its many phases, especially, in triage of relevant documents and extraction of named entities and biological events. Here, we present the curation pipeline of the CellFin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
14
0

Year Published

2013
2013
2019
2019

Publication Types

Select...
7
1

Relationship

3
5

Authors

Journals

citations
Cited by 14 publications
(14 citation statements)
references
References 63 publications
(69 reference statements)
0
14
0
Order By: Relevance
“…Such techniques have limited accuracy and are often used prior to manual validations (21,22). Alkemio relies on manually set MeSH (15) annotations that may not be comprehensive, but that are of the highest quality.…”
Section: Discussionmentioning
confidence: 99%
“…Such techniques have limited accuracy and are often used prior to manual validations (21,22). Alkemio relies on manually set MeSH (15) annotations that may not be comprehensive, but that are of the highest quality.…”
Section: Discussionmentioning
confidence: 99%
“…In that work, gene names were tagged using dictionary-matching and a set of rules was devised to identify sentences with potentially relevant information about gene expression. There have also been studies on identifying genes expressed in cell types [21] and anatomical locations [22], or in both [23]. The identification of sentences that describe gene expression, without any other contextual details, has also been addressed as part of more-general event extraction tasks [24, 25].…”
Section: Methodsmentioning
confidence: 99%
“…This resulted in a modest improvement over TEES, leading to a first place in the GE task of the 2013 BioNLP-ST competition, with an F-score of 50.97%. Other applications of TEES include its use in: the CellFinder literature curation pipeline [45], the BioContext integrated text mining system [46], and semi-automated knowledge extraction workflow [47]. With growing interest towards adopting such open source tools as modules in larger BioNLP systems, TEES is a leading event extraction system that can be further improved on by incorporation of more advanced coreference resolution techniques, and addition of methods for adaptive learning from multiple corpora to detect events spanning multiple sentences from heterogeneous texts.…”
Section: Event Extraction Methodologiesmentioning
confidence: 99%