Computational Linguistic Techniques Applied to Drugname Matching

1
Computational Linguistic Techniques Applied to
Drugname Matching
Bonnie J. Dorr, University of Maryland Greg
Kondrak, University of Alberta June 26, 2003
2
Drugname Matching

• String matching to rank similarity between drug
  names
• Two classes of string matching
• orthographic Compare strings in terms of
  spelling without reference to sound
• phonological Compare strings on the basis of a
  phonetic representation
• Two methods of matching
• distance How far apart are two strings?
• similarity How close are two strings?

3
Distance and Similarity Measures Orthographic/
Phonological

• Orthographic
• Distance string-editEx contac / zantac 2/6
  0.33
• Similarity LCSR, DICEEx contac / zantac 4/6
  0.66Ex co on nt ta ac / za an nt ta ac 6/12
  0.50
• Phonological
• Distance SoundexEx contac/zantac 1/4 0.25
• Similarity ALINEEx contac/zantac 0.64

4
Distance vs. Similarity Examples

• Example 1 hordes vs lords
• Distance 2 (replace h with l, and delete e).
• Similarity 2 (bigrams or and rd in common).
• Example 2 water vs wine
• Distance 3 (replace a w/ i, t w/ n, delete r).
• Similarity 0 (no bigrams in common).
• We can compare (global) similarity and distance
• sim(w1,w2)/length
• 1 - dist(w1,w2)/length

5
Orthographic Distance string-edit

• Count up the number of steps it takes to
  transform one string into another
• Examples
• Distance between hordes and lords is 2.
• Distance between water and wine is 3.
• For global distance, we can divide by length of
  longest string 2/6 and 3/5 above

6
Orthographic Similarity LCSR, DICE

• LCSR Divide length of longest common
  sub-sequence by length of longest string
• Example reagir and repair have longest common
  subsequence reair.Similarity score 5/max(6,6)
  5/6 0.83
• DICE Double the number of shared character
  bigrams and divide by total number of bigrams in
  each string
• Example reagir and repair have bigram sets
  re,ea,ag,gi,ir and re,ep,pa,ai,ir,
  respectively, and shared bigrams are re,ir.
  Similarity score (2 2)/(55) 2/5 0.40

7
Phonological Matching

• Distance-based phonological matching
• Soundex
• Similarity-based phonological matching
• ALINE

8
Phonological Distance

• Soundex Examples
• king and khyngge reduce to k52
• knight and night reduce to k523 and n23
• pulpit and phlebotomy reduce to p413

9
What went wrong?

• Truncation of word to four characters
• Alternative Use entire string
• Ignoring vowels
• Use more sophisticated phonetic rules
• Using numbers instead of decomposable features
• Use decomposable features

10
Phonological Similarity

• Another possible approach Compare syllable
  count, initial/final sounds, stress locations
• Misses frequently confused pairs
• Alternative Use phonological features to compare
  two words by their sounds.
• x?k(s) consonantal, velar, stop, -voice
• x?z consonantal, alveolar, fricative,
  voice
• Phonological similarity of two words Optimal
  match between their phonological features.
• Zantac
• Xanax

11
Kondrak ALINE (2000)

• Two fundamental components of ALINE
• Similarity Function Uses linguistic feature
  analysis measurements based on salience, e.g.,
  alveolar and stop more salient than voice
• Method for choosing optimal alignment creates
  alignment based on a weighted multi-feature
  analysis
• Designed to align phonetic sequences for many
  different CL applications
• Developed originally for identifying cognates in
  vocabularies of related languages (e.g., colour,
  couleur)
• Feature weights can be fine-tuned for specific
  application.
• Efficient Dynamic programming algorithm
  quadratic

12
ALINE Features Weights and Values
13
Places of Articulation Numerical Values
14
Manner of ArticulationNumerical Values

• stop 1.0Example p, b
• affricate 0.9Example th
• fricative 0.8Example f, v

15
Tuning of ALINE Parameters

• Parameters have default settings for cognate
  matching task, but not appropriate for drugname
  matching
• Parameter tuning
• calculate weights for drugname matching
• Hill Climbing search against gold standard
• Tuned parameters for drugname task
• maximum score
• insertion/deletion penalty
• vowel penalty
• phonological feature values

16
Comparison of Outputs

• ALINE 0.792 zantac xanax 0.639
  zantac contac 0.486 xanax contac
• EDIT 0.500 zantac xanax 0.667
  zantac contac 0.333 xanax contac
• LCSR 0.545 zantac xanax 0.667
  zantac contac 0.364 xanax contac
• DICE 0.222 zantac xanax 0.600
  zantac contac 0.000 xanax contac

17
Evaluation

• Precision and recall against online gold
  standard USP Quality Review, Mar, 2001.
• 582 unique drug names, 399 true confusion pairs,
  169,071 possible pairs (combinatorically induced)
• Example (using DICE) 0.889
  atgam ratgam 0.875 herceptin perceptin-
  0.870 zolmitriptan zolomitriptan
  0.857 quinidine quinine- 0.857
  cytosar cytosar-u 0.842
  amantadine rimantadine
  - 0.800
  erythrocin erythromycin

18
Comparison of Precision at Different Recall Values
19
Precision of Techniques withPhonetic
Transcription
20
Conclusion

• Experimentation with different algorithms and
  their combinations against gold standard.
• ALINE Strong foundation for search modules in
  automating the minimization of medication errors
• Fine-tuning based on comparisons with gold
  standard (e.g., re-weighting of phonological
  features).
• Related to pattern recognition Discover patterns
  of predictable matches based on feature values