A Simple Algorithm for Identifying Abbreviation Definitions in Biomedical Text

By Ariel S. Schwartz, Marti A. Hearst. Pacific Symposium on Biocomputing, 2002

616 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/44e9739e35a80c71e61b4e08871585ba75da2d2b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Impact of license choice on Open Source Software development activity (2009, methodology): “Acronyms and their long forms are identified during preprocessing using the Schwartz and Hearst algorithm ( Schwartz & Hearst, 2003 ).”
History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining (2018, methodology): “A text mining algorithm similar to the one proposed by Schwartz and Hearst (2003) is used to retrieve all abbreviations.”
BANNER: An Executable Survey of Advances in Biomedical Named Entity Recognition (2007, methodology): “This format can be detected with a high degree of accuracy by a simple algorithm [12], whi ch then triggers”
Overview of BioCreative II gene mention recognition (2008, methodology): “Before training or tagging the sentences, they were passed through a series of linguistic preprocessing stages, including tokenization, lemmatization, part of speech tagging, chunking and abbreviation detection (using the Schwartz and Hearst abbreviation detector [26]).”
Biomedical text mining and its applications in cancer research (2013, neutral): “BioText [178–184] BioText was initially constructed by 1000 randomly selected MEDLINE abstracts from the results of a query on the term yeast.”
Term identification in the biomedical literature (2004, background): “Schwartz and Hearst [58] suggested a general algorithm for the extraction of the shortest corresponding EF for a given acronym.”
An overview of MetaMap: historical perspective and recent advances (2010, background): “43 We try to match a potential AA, which must be bracketed (eg, (ACTH)) with a potential expansion, which must precede the AA in the same sentence (eg, adrenocorticotropic hormone).”
Content-rich biological network constructed by mining PubMed abstracts (2004, background): “[37-40]] have been developed to translate acronyms unambiguously into their full length terminology, since acronyms may have multiple meanings and become a source of false positives [3,41].”
ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing (2019, methodology): “To partially remedy this, we implement the unsupervised abbreviation detection algorithm of Schwartz and Hearst (2002), substituting mention candidates marked as abbreviations for their long form definitions before searching for their nearest neighbours.”
Overview of BioCreative II gene normalization (2008, methodology): “used the Schwartz and Hearst algorithm [31] for detecting”
A survey of current work in biomedical text mining (2005, methodology): “of 88.5%. Yu et al. [46] and Schwartz and Hearst [ 28 ] applied manually created set of”
Getting More Out of Biomedical Documents with GATE's Full Lifecycle Open Source Text Analytics (2013, methodology): “BADREX (identifying B iomedical A bbreviations using D ynam-ic R egular E xpressions) [55] is a GATE plugin that annotates, expands and corefers term-abbreviation pairs using parameteri-sable regular expressions that generalise and extend the Schwartz-Hearst algorithm [56].”