Ontology alignment

Patrick Lambrix

Linköpings universitet

Strategies based on linguistic matching Structure-based strategies Constraint-based approaches Instance-based strategies Use of auxiliary information Combining different approaches

Alignment Strategies Strategies based on linguistic matchingStrategies based on linguistic matching

SigO: complement signaling synonym complement activation

GO: Complement Activation

Alignment Strategies Strategies based on linguistic matching Structure-based strategiesStructure-based strategies Constraint-based approaches Instance-based strategies Use of auxiliary information Combining different approaches

Alignment Strategies Strategies based on linguistic matching Structure-based strategies Constraint-based approachesConstraint-based approaches Instance-based strategies Use of auxiliary information Combining different approaches

O1O2

Person

Animal Animal

Human

Alignment Strategies Strategies based on linguistic matching Structure-based strategies Constraint-based approaches Instance-based strategiesInstance-based strategies Use of auxiliary information Combining different approaches

Ontology

instancecorpus

Alignment Strategies Strategies based linguistic matching Structure-based strategies Constraint-based approaches Instance-based strategies Use of auxiliary informationUse of auxiliary information Combining different approaches

thesauri

alignment strategies

dictionary

intermediateontology

Alignment Strategies Strategies based on linguistic matching Structure-based strategies Constraint-based approaches Instance-based strategies Use of auxiliary information Combining different approachesCombining different approaches

Ontology A

lignment and M

ergning S

ystems

An Alignment Framework

Evaluation - casesGO vs. SigO

MA vs. MeSH

GO-immune defense

GO: 70 terms SigO: 15 terms

SigO-immune defense GO-behaviorGO: 60 terms SigO: 10 terms

SigO-behavior

MA-eyeMA: 112terms MeSH: 45 terms

MeSH-eye

MA-noseMA: 15 terms MeSH: 18 terms

MeSH-nose MA-earMA: 77 terms MeSH: 39 terms

MeSH-ear

Evaluation Matchers

Term, TermWN, Dom, Learn (Learn+structure), Struc

ParametersQuality of suggestions: precision/recall

Threshold filtering : 0.4, 0.5, 0.6, 0.7, 0.8

Weights for combination: 1.0/1.2

KitAMO (http://www.ida.liu.se/labs/iislab/projects/KitAMO)

Evaluation

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

threshold

prec

isio

n

B

ID

nose

ear

eye

Terminological matchers

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

threshold

reca

ll

B

ID

nose

ear

eye

Evaluation Basic learning matcher

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

threshold

reca

ll

B

ID

nose

ear

eye

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

thresholdpr

ecis

ion

B

ID

nose

ear

eye

Evaluation

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

threshold

prec

isio

n

B

ID

nose

ear

eye

Domain matcher

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0.4 0.5 0.6 0.7 0.8

threshold

reca

ll

B

ID

nose

ear

eye

Evaluation Comparison of the matchers

CS_TermWN CS_Dom CS_Learn

Combinations of the different matchers

combinations give often better results no significant difference on the quality of suggestions for different

weight assignments in the combinations

Structural matcher did not find (many) new correct alignments

(but: good results for systems biology schemas SBML – PSI MI)

Evaluation Matchers

TermWN

ParametersQuality of suggestions: precision/recall

Double threshold filtering using structure: Upper threshold: 0.8

Lower threshold: 0.4, 0.5, 0.6, 0.7, 0.8

Chen, Tan, Lambrix, Structure-based filtering for ontology alignment,IEEE WETICE workshop on semantic technologies in collaborative applications, pp 364-369, 2006.

Evaluation The precision is increased after filtering.

- a linguistic alignment algorithm using WordNet

- the upper threshold is 0.8

eye

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0,4 0,5 0,6 0,7

(lower) threshold

prec

isio

n

TermWN

filtered

Evaluation The recall is constant in most cases after filtering

eye

0

0,1

0,2

0,3

0,4

0,5

0,6

0,7

0,8

0,9

1

0,4 0,5 0,6 0,7 0,8

(lower) threshold

reca

ll

TermWN

filtered

- a linguistic alignment algorithm using WordNet

- the upper threshold is 0.8

Issues

Evaluation methodology: Golden standards

e.g. OAEI: Anatomy (FMA – GALEN) Systems available, but not always the alignment

algorithms. Connections types of algorithms – types of

ontologies Recommending ’best’ alignment strategies

Further reading

http://www.ontologymatching.org Ontology alignment evaluation initiative:

http://oaei.ontologymatching.org

Lambrix, Tan, SAMBO – a system for aligning and merging biomedical ontologies, Journal of Web Semantics, 4(3):196-206, 2006.

Lambrix, Tan, A tool for evaluating ontology alignment strategies, Journal on Data Semantics, VIII:182-202, 2007.