Dictionarybased Approaches for Biomedical Term Recognition

1
Dictionary-based Approaches for Biomedical Term
Recognition

• Yoshimasa Tsuruoka
• CREST, JST
• (Japan Science and Technology Corporation)

2
Outline

• Dictionary-based protein name recognition
• Approximate string searching
• Filtering by a naïve Bayes classifier
• Probabilistic Term Variant Generator
• Generation Algorithm
• Application Dictionary expansion

3
Background

• Information extraction from biomedical documents
• Recognizing technical terms (e.g. DNA, protein
  names)
• We measured glucocorticoid receptors ( GR )
• in mononuclear leukocytes ( MNL ) isolated

4
Technical Term Recognition

• Machine learning based
• Identifying the regions of terms
• ? No ID information
• Dictionary-based
• Comparing the strings with each entry in the
  dictionary
• ? ID information

5
Problems of Dictionary-based approaches

• Spelling variation degrades recall
• ? Approximate string searching
• False positives degrade precision
• ? Filtering by machine learning

6
Exact String Searching

• Example
• Text
• Phorbol myristate acetate induced Egr-1 mRNA
• Dictionary
• EGP
• EGR-1
• EGR-1 binding protein
• ? Any of them does not match

7
Edit Distance

• Defines the distance of two strings by the
  sequence of three kinds of operations.
• Substitution
• Insertion
• Deletion
• Ex.) board ? abord
• Cost 2 (delete a and add a)

8
Weighted Edit Distance

• Uniform-cost edit distance is not appropriate
• The distance of the first pair should be smaller
  than that of the second one.
• ? Weighted Edit Distance

EGR-1 ? EGR 1 cost 1 EGR-1 ? FGR-1 cost
1
9
Calculating Weighted Edit Distance by Dynamic
Programming

• Dynamic Programming Matrix

10
Approximate String Searching

• Setting zeros at the positions of separators in
  the first row

11
Recognizing Terms

• To Consider the length of a string
• Normalized Cost
• ? Longer strings are preferred

12
Cost Table
13
Filtering by Machine Learning

• Classify each recognized terms into two classes.

induced Egr-1 mRNA
rejected
accepted
Protein name
14
Features for Classification

• Features
• Contextual features
• Term features
• Ex.)
• encoding a putative zinc finger protein was
  found to derepress beta-galactosidase
• W-1 a, W1 was, Wbegin putative,Wend
  protein, Wmiddle zinc, Wmiddle finger

15
ExperimentProtein Name Recognition

• Corpus GENIA corpus 3.01
• For training 1800 abstracts
• For testing 200 abstracts
• Class Protein
• Innermost tags
• Dictionary constructed from training data
• Classifier Naïve Bayes Model

16
Experimental Results
Exact matching
Filtering Approximate String Searching
17
Feature
Filtering Approximate String Searching (th.
6.0)
18
Automatic Generation of Spelling Variants

• Variant Generator

• NF-Kappa B (1.0)
• NF Kappa B (0.9)
• NF kappa B (0.6)
• NF kappaB (0.5)
• NFkappaB (0.3)

Generator
NF-Kappa B
Each generated variant has its generation
probability
19
Generation Algorithm

• Recursive generation
• P P x Pop

T cell (1.0)
0.5
0.2
T-cell (0.5)
T cells (0.2)
0.2
T-cells (0.1)
20
Gathering Examples of Spelling Variation

• Abbreviation Extraction (Schwartz 2003)
• Extracts short and long form pairs

21
Learning Operation Rules

• Operations for generating variants
• Substitution
• Deletion
• Insertion
• Context
• Character-level context preceding (following)
  two characters
• Operation Probability

22
Probabilistic Rules
23
Example (1)
24
Example (2)
25
Example (3)
26
ApplicationDictionary Expansion

• Expanding each entry in the dictionary
• Threshold of Generation Probability 0.1
• Max number of variants for each entry 20

27
Conclusion

• Dictionary-based Term Recognition
• For boosting precision Filtering
• For boosting recall Approximate string searching
• Probabilistic Variant Generator
• Learning from actual examples
• Dictionary expansion by the generator improves
  recall without the loss of precision.