OWL2Vec*: embedding of OWL ontologies
Semantic embedding of knowledge graphs has been widely studied and used for prediction and statistical analysis tasks across various domains such as Natural Language Processing and the Semantic Web. However, less attention has been paid to developing robust methods for embedding OWL (Web Ontology La...
| Glavni autori: | , , , , , |
|---|---|
| Format: | Journal article |
| Jezik: | English |
| Izdano: |
Springer
2021
|
| _version_ | 1826310147522166784 |
|---|---|
| author | Chen, J Hu, P Jimenez-Ruiz, E Holter, OM Antonyrajah, D Horrocks, I |
| author_facet | Chen, J Hu, P Jimenez-Ruiz, E Holter, OM Antonyrajah, D Horrocks, I |
| author_sort | Chen, J |
| collection | OXFORD |
| description | Semantic embedding of knowledge graphs has been widely studied and used for prediction and statistical analysis tasks across various domains such as Natural Language Processing and the Semantic Web. However, less attention has been paid to developing robust methods for embedding OWL (Web Ontology Language) ontologies, which contain richer semantic information than plain knowledge graphs, and have been widely adopted in domains such as bioinformatics. In this paper, we propose a random walk and word embedding based ontology embedding method named OWL2Vec*, which encodes the semantics of an OWL ontology by taking into account its graph structure, lexical information and logical constructors. Our empirical evaluation with three real world datasets suggests that OWL2Vec* benefits from these three different aspects of an ontology in class membership prediction and class subsumption prediction tasks. Furthermore, OWL2Vec* often significantly outperforms the state-of-the-art methods in our experiments. |
| first_indexed | 2024-03-07T07:46:15Z |
| format | Journal article |
| id | oxford-uuid:f993a116-69c3-4cca-8f82-3f8c006d3c9c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:46:15Z |
| publishDate | 2021 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:f993a116-69c3-4cca-8f82-3f8c006d3c9c2023-06-08T06:26:32ZOWL2Vec*: embedding of OWL ontologiesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:f993a116-69c3-4cca-8f82-3f8c006d3c9cEnglishSymplectic ElementsSpringer2021Chen, JHu, PJimenez-Ruiz, EHolter, OMAntonyrajah, DHorrocks, ISemantic embedding of knowledge graphs has been widely studied and used for prediction and statistical analysis tasks across various domains such as Natural Language Processing and the Semantic Web. However, less attention has been paid to developing robust methods for embedding OWL (Web Ontology Language) ontologies, which contain richer semantic information than plain knowledge graphs, and have been widely adopted in domains such as bioinformatics. In this paper, we propose a random walk and word embedding based ontology embedding method named OWL2Vec*, which encodes the semantics of an OWL ontology by taking into account its graph structure, lexical information and logical constructors. Our empirical evaluation with three real world datasets suggests that OWL2Vec* benefits from these three different aspects of an ontology in class membership prediction and class subsumption prediction tasks. Furthermore, OWL2Vec* often significantly outperforms the state-of-the-art methods in our experiments. |
| spellingShingle | Chen, J Hu, P Jimenez-Ruiz, E Holter, OM Antonyrajah, D Horrocks, I OWL2Vec*: embedding of OWL ontologies |
| title | OWL2Vec*: embedding of OWL ontologies |
| title_full | OWL2Vec*: embedding of OWL ontologies |
| title_fullStr | OWL2Vec*: embedding of OWL ontologies |
| title_full_unstemmed | OWL2Vec*: embedding of OWL ontologies |
| title_short | OWL2Vec*: embedding of OWL ontologies |
| title_sort | owl2vec embedding of owl ontologies |
| work_keys_str_mv | AT chenj owl2vecembeddingofowlontologies AT hup owl2vecembeddingofowlontologies AT jimenezruize owl2vecembeddingofowlontologies AT holterom owl2vecembeddingofowlontologies AT antonyrajahd owl2vecembeddingofowlontologies AT horrocksi owl2vecembeddingofowlontologies |