This paper describes EVOCROS, a cross-lingual ontology alignment system suited to create mappings between ontologies described in di erent natural language. Our tool combines semantic and syntactic similarity measures in a weighted average metric. The semantic is computed via NASARI vectors used together with BabelNet, which is a domain-neutral semantic network. The tool employs automatic translation to a pivot language to consider the similarity. EVOCROS was tested and obtained high quality alignment in the Multifarm dataset. We discuss the experimented con gurations and the achieved results in OAEI 2018. This is our rst participation in OAEI.
1.1
EVOCROS is a cross-lingual ontology alignment tool based on a composed similarity measure relying on both syntactic and semantic similarity techniques. Syntactic similarity may be understood as a score calculated based on string analysis (extracted from labels of concepts), whereas the semantic similarity is computed taking into account background knowledge. Our approach computes a weighted mean of semantic and syntactic similarities. 1.2
The tool is developed in Python 3. It works by comparing the computed
similarity between a concept from an ontology (in its automatically translated version)
to another concept from a di erent ontology. The concept terms are translated to
a pivot natural language aiming to use available external resources such as
thesauri, corpora, dictionaries, etc. to overcome the language and alphabet barriers.
3 Python 3 library to manipulate ontologies as objects.
Syntactic Similarity Measure. For syntactic similarity measure, the concept
labels of both the source and target ontologies are rst translated to a pivot
language using automatic translation. We are using English as pivot language
for OAEI 2018 though the tool accepts any language as pivot. The concepts are
then compared by measuring the syntactic similarity via edit distance
Levenshtein [
Semantic Similarity Measure. Semantic similarity between terms is a metric to evaluate how similar two given terms are considering their meanings in a certain context. For example, the words \nail" and \hammer" are more similar considering the tool context than \nail" and \ nger". On the other hand, when we consider the anatomy context, \nail" and \ nger" are more similar than \nail" and \hammer".
For semantic similarity, we use the concept label in its original language,
without any translation. There are a lot of algorithms to calculate semantic
similarity. These algorithms usually explore an external resource such as vocabulary,
dictionaries or thesauri to help computing the similarity between two words.
EVOCROS explores a Weighted Overlap measure [
Our proposal generates cross-lingual ontology alignments taking into account the combination of semantic and syntactic similarity by computing the weighted average as follows: De nition 1 (Composed Similarity). Let sem(t1, t2) and sin(t1, t2) be the semantic similarity, and the syntactic one between the terms t1 and t2, respectively. We assume that the similarities are normalized between 0 and 1. Formally: simC(t1; t2) = sin(t1; t2) + sem(t1; t2) + (1) where and
are constants.
If the weighted similarity reaches a threshold, the concept pair is recorded to the output le, generated in RDF format. Otherwise, it is discarded. 1.3
EVOCROS uses a con guration le with the source and target ontologies, and their respective language. In order to participate in OAEI, we modi ed the tool to receive the source and target ontologies as input parameters and retrieve the ontology language from the lang XML tag. The bridge created for SEALS platform is written in Java and executed system calls to run the tool, written in Python 3. Although the tool executed locally using the SEALS client, there were issues during evaluation on SEALS platform and only local results are available in this report. 1.4
Alignment results are available at https://github.com/jmdestro/evocros-results. 2
In this section, we describe the results obtained from local experiments using a sub-set of Multifarm with the same con guration used in OAEI 2018 evaluation. 2.1
Our experiments were based on ontologies from conference domain from the
MultiFarm dataset 2015 [
Several weights for similarity measures and di erent similarity thresholds were evaluated locally. For OAEI 2018, only the following con guration was submitted: threshold: 0.66, syntactic similarity weight: 0.75, semantic similarity weight: 0.25. This was the con guration with the most interesting results. Table 1 presents the used con guration and the results for conference-conference alignment for languages spanish-portuguese (es-pt) and english-portuguese (enpt).
The choice of weights assigned to each similarity measure played an important role in the results. Tables 2 and 3 present the obtained results for di erent con gurations. Considering the syntactical weights as 0.75 and 0.80 generated the best mappings, that is, they result in alignments with the greatest f-measure. Thus, our technique may be understood as a good alternative to syntactic or semantic only methods, and it might perform even better taking into account the correct parameters. The tool had satisfactory results but the execution time was exceedingly long due to constant RestAPI calls to Babelnet. The results showed an in uence of threshold: as the threshold rises, the precision also increases. It may be explained by considering equivalence of only those concepts with a high level of similarity. However, f-measure declines as the threshold increases because large values assigned to threshold make the algorithm disregards concepts that are equivalent, but somehow was assigned a lower level of similarity than expected by the threshold. As a result, the recall drops substantially, because many correct correspondences are ignored, and thus f-measure decreases. Empirically, we concluded that the thresholds that generate the more accurate mappings were = 0:75.
This was the rst evaluation of the system and although there was issues during
the evaluation phase of OAEI, preventing the system to be executed in SEALS
platform, the local results are encouraging. Our main goals for future work are:
Reduce execution time: the tool has a long execution time due to constant
RestAPI calls to Babelnet and needs to be optimized with local caches.
Bag of graphs: ontologies can be represented as graphs, thus allowing for
partitioning [
There were issues during the evaluation phase, preventing the system to participate in Multifarm track. For future editions of OAEI, we plan to participate submitting EVOCROS on the newly available HOBBIT platform, using a docker image, to ensure system compatibility during evaluation. 4
EVOCROS proposed an approach to cross-lingual ontology matching by combining semantic and syntactic similarity measures. This is the rst participation of the system in OAEI. The evaluation with the Multifarm dataset con rmed the quality of mappings generated by our technique. For future work, we plan to improve our cross-lingual ontology alignment proposal considering di erent combinations of background knowledge, such as speci c-domain thesauri to evaluate the semantic similarity. We also plan to further evaluate runtime optimization aspects to x issues found during the evaluation phase.
This work has been supported by S~ao Paulo Research Foundation (FAPESP): grants #2017/23522-3 and #2017/02325-5.