Ontology Alignment Evaluation Initiative

OA4QA Track

OAEI 2014::Ontology Alignment for Query Answering (OA4QA)

Global Evaluation Results

Summary table showing the averaged precision/recall/f-measure results for the whole set of queries: AML, LogMap, LogMapC and XMap were the only matchers whose alignments allowed to answer all the queries of the evaluation.

LogMap was the best performing tool for what concerns averaged precision, recall and f-measure, closely followed by LogMapC and AML. XMap, despite being able to produce an alignment not leading to unsatifiabilities during query answering, did not achieve optimal results.

The difference in results between the publicly available reference alignment of the Conference track (RA1) and its repaired version (RAR1, not to be confused with RA2 of the Conference track) was not significant and, as expected, affected precision. The f-measure ranking between the two reference alignments is preserved, but RAR2 highlights the gap between the top-4 matcher and the others, and it also allows to differentiate more among the least performing matchers.

Detailed Evaluation Results

Precision Evaluation Results

Detailed table showing precision results for each query:

Recall Evaluation Results

Detailed table showing recall results for each query:

F-measure Evaluation Results

Detailed table showing f-measure results for each query: