We have collected all generated alignments and make them available in a zip-file via the following link. These alignments are the raw results that the following report is based on.
We conducted experiments by executing each system in its standard setting and we compare precision, F-measure, recall and recall+. The measure recall+ indicates the amount of detected non-trivial correspondences. The matched entities in a non-trivial correspondence do not have the same normalized label.
We ran the matchers on a machine with 16GB RAM installed. As last two years, we used the MELT platform to execute our evaluations for all systems except ALIN and AMD that we used the SEALS client.
As in earlier years, we slightly changed the way how precision and recall are computed, i.e., the results generated by the MELT and SEALS clients vary in some cases by 0.5% compared to the results presented below. In particular, we removed trivial correspondences in the oboInOwlnamespace like
http://...oboInOwl#Synonym = http://...oboInOwl#Synonym
as well as correspondences expressing relations different from equivalence.
Using the Pellet reasoner we also checked whether the generated alignment is coherent, i.e., there are no unsatisfiable concepts when the ontologies are merged with the alignment.
In the following, we analyze all participating systems that could generate an alignment. The listing comprises of 9 entries. LogMap participated with different versions, namely LogMap, LogMapBio, and a lightweight version LogMapLite that uses only some core components as previous years. There are two systems, SORBETMtch and OLaLa participating in the anatomy track this year for the first time. Matcha has participated in the anatomy track for the second time. The rest of the systems have participated in OAEI for more than two years. From the systems participating this year, ALIN , LSMatch, AMD, Matcha and LogMap (all versions) participated last year as well. LogMap is a constant participant since 2011 and ALIN joined in 2016. For more details, we refer the reader to the papers presenting the systems. Thus, this year we have 7 different systems (not counting different versions) which generated an alignment.
This year 5 out of 9 systems were able to achieve the alignment task in less than 100 seconds (they require between 3 and 54 seconds to match the ontologies). These are LogMapLite, LogMap, LSMatch, AMD and Matcha. In 2022 and 2021, there were 4 out of 10 and 6 out of 15 systems respectively which generated an alignment in this time frame. Similarly to the last 11 years, LogMapLite has the shortest run time (3 seconds). The table shows that there is no correlation between the required time for running and the quality of the generated alignment in specific metric. This result has also been observed in previous OAEI campaigns.
The table also shows the results for F-measure, recall+ and the size of the alignments. Regarding F-measure, the top 3 ranked systems are Matcha, OLaLa and SORBETMtch. Among these, Matcha achieved the highest F-measure (0.941) which is the same as last year. This year, except LogMapBio with a slight increase from 0.895 in 2022 to 0.898 in 2023, other systems participating last year did not show any increase in F-measure. Regarding recall+, ALIN, LSMatch, LogMap and LogMapLite show similar results as earlier. Matcha had a minor increase on recall+ from 0.817 in 2022 to 0.818 in 2023. OLaLa and SORBETMtch as new systems in 2023 show high values for recall+ (0.726 and 0.724 respectively). Regarding the number of correspondences, ALIN, LSMatch, LogMap and LogMapLite computed a similar number of correspondences as last year. Compared with last year's results, Matcha generated 2 more correspondences, AMD generated 17 less, and LogMapBio generated 18 less, respectively.
This year 8 out of 9 systems achieved a F-measure higher than the baseline which is based on (normalized) string equivalence (StringEquiv in the table). Among these 8 systems, SORBETMtch and OLaLa are new participants.This year two systems produced coherent alignments which are LogMap and LogMapBio.
The number of participating systems varies between the years. In 2023, there are one and six participants less than the number of participants in 2022 and 2021 respectively. As noted earlier there are newly-joined systems as well as long-term participants.
This year, Matcha sets the top result for the anatomy track with respect to the F-measure, followed by OLaLa and SORBETMtch.
This track is organized by Mina Abd Nikooie Pour, Huanyu Li, Ying Li, and Patrick Lambrix. If you have any problems working with the ontologies, any questions related to tool wrapping, or any suggestions related to the anatomy track, feel free to write an email to oaei-anatomy [at] ida [.] liu [.] se.