Identifying Abbreviation Definitions in Biomedical Text

1
Identifying Abbreviation Definitions in
Biomedical Text

• Ariel Schwartz Marti Hearst

2
The Problem

• The volume of biomedical text is growing at a
  fast rate. New abbreviations are introduced
  frequently.
• Manual abbreviation dictionaries are out of date.
• The goal is to have a simple, fast and accurate
  algorithm to identify abbreviations and their
  definitions in biomedical text.
• We are interested in this algorithm, as one of
  many preprocessing steps we apply to biomedical
  texts, in order to be able to extract meaningful
  information from these texts.

3
Abbreviation Examples

• Heat-shock protein 40 (Hsp40) enables Hsp70 to
  play critical roles in a number of cellular
  processes, such as protein folding, assembly,
  degradation and translocation in vivo.
• Glutathione S-transferase pull-down experiments
  showed the direct interaction of in vitro
  translated p110, p64, and p58 of the essential
  CBF3 kinetochore protein complex with Cbf1p, a
  basic region helix-loop-helix zipper protein
  (bHLHzip) that specifically binds to the CDEI
  region on the centromere DNA.
• Hpa2 is a member of the Gcn5-related
  N-acetyltransferase (GNAT) superfamily, a family
  of enzymes with diverse substrates including
  histones, other proteins,arylalkylamines and
  aminoglycosides.

4
Related Work

• Pustejovsky et al. present a solution based on
  hand-build regular expression and syntactic
  information. Achieved 72 recall at 98
• Chang et al. use linear regression on a
  pre-selected set of features. Achieved 83 recall
  at 80 precision, and 75 recall at 95
  precision.
• Park and Byrd present a rule-based algorithm for
  extraction of abbreviation definitions in general
  text.
• Yoshida et al. present an approach close to ours,
  trying to first match characters on word and
  syllable boundaries.

Counting partial matches, and abbreviations
missing from the gold-standard their algorithm
achieved 83 recall at 98 precision.
5
The Algorithm

• Much simpler than other approaches.
• Extracts abbreviation-definition candidates
  adjacent to parentheses.
• Finds correct definitions by matching characters
  in the abbreviation to characters in the
  definition, starting from the right.
• The first character in the abbreviation must
  match a character at the beginning of a word in
  the definition.
• To increase precision a few simple heuristics are
  applied to eliminate incorrect pairs.
• Example Heat shock transcription factor (HSF).
• The algorithm finds the correct definition, but
  not the correct alignment Heat shock
  transcription factor

6
Results

• On the gold-standard the algorithm achieved 83
  recall at 96 precision.
• On a larger test collection the results were 90
  recall at 95 precision.
• An alternative algorithm, based on modification
  of the Park and Byrd algorithm using decision
  lists, achieved only slightly better results
  83 recall at 97 precision, and 90 at 96
  precision.
• These results show that a very simple algorithm
  produces results that are comparable to these of
  the exiting more complex algorithms.

Counting partial matches, and abbreviations
missing from the gold-standard our algorithm
achieved 83 recall at 99 precision.