@inproceedings{MTMT:33191477, title = {Knowledge Enriched Schema Matching Framework for Heterogeneous Data Integration}, url = {https://m2.mtmt.hu/api/publication/33191477}, author = {Ma, Chuangtao and Molnár, Bálint and Tarcsi, Ádám and Benczúr, András, id}, booktitle = {2022 IEEE 2nd Conference on Information Technology and Data Science (CITDS)}, doi = {10.1109/CITDS54976.2022.9914350}, unique-id = {33191477}, year = {2022}, pages = {183-188}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} } @article{MTMT:31788843, title = {Ontology Learning from Relational Database: Opportunities for Semantic Information Integration}, url = {https://m2.mtmt.hu/api/publication/31788843}, author = {Ma, Chuangtao and Molnár, Bálint}, doi = {10.1142/S219688882150024X}, journal-iso = {VIETNAM J COMP SCI}, journal = {VIETNAM JOURNAL OF COMPUTER SCIENCE}, volume = {9}, unique-id = {31788843}, issn = {2196-8888}, abstract = {Along with the rapidly growing scale of relational database(RDB), how to construct domain-related ontologies from various database effectively and efficiently have being a bottleneck of the ontology-based integration. The traditional methods for construct- ing ontology from RDB are mainly based on the manual mapping and transformation, which not only requires a lot of human experience but also easily lead to the semantic loss during the transformation. Ontology learning from RDB is a new paradigm to (semi- )automatically construct ontologies from RDB by borrowing the techniques of machine learning, it provides a potential opportunities for integrating heterogeneous data from various data sources efficiently. This paper surveys the recent methods and tools of the ontology learning from RDB, and highlights the potential opportunities and challenges of using ontology learning in semantic information integration. Initially, the previous surveys on the topic of the ontology-based integration and ontology learning were sum- marized, and then the limitations of previous surveys were identified and analyzed. Fur- thermore, the methods and techniques of ontology learning from RDB were investigated by classifying into three categories: reverse engineering, mapping, and machine learning. Accordingly, the opportunities and possibility of using ontology learning from RDB in semantic information integration were discussed based on the mapping results between the bottlenecks of ontology-based integration and the features of ontology learning}, year = {2022}, eissn = {2196-8896}, pages = {31-57}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} } @article{MTMT:31989908, title = {A Semi-automatic Semantic Consistency-Checking Method for Learning Ontology from Relational Database}, url = {https://m2.mtmt.hu/api/publication/31989908}, author = {Ma, Chuangtao and Molnár, Bálint and Benczúr, András, id}, doi = {10.3390/info12050188}, journal-iso = {INFORMATION-BASEL}, journal = {INFORMATION (BASEL)}, volume = {12}, unique-id = {31989908}, year = {2021}, eissn = {2078-2489}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} } @techreport{MTMT:31830781, title = {Knowledge-enriched Schema Mapping: A Preliminary Case Study of e-MedSolution System}, url = {https://m2.mtmt.hu/api/publication/31830781}, author = {Ma, Chuangtao}, editor = {Molnár, Bálint and Tarcsi, Ádám}, unique-id = {31830781}, year = {2020}, orcid-numbers = {Molnár, Bálint/0000-0001-5015-8883; Ma, Chuangtao/0000-0002-6492-2579} } @CONFERENCE{MTMT:31814813, title = {Semantic Consistency behind Ontology Learning and Schema Mapping for Heterogeneous Data Integration}, url = {https://m2.mtmt.hu/api/publication/31814813}, author = {Ma, Chuangtao and Molnár, Bálint}, booktitle = {Collection of Abstracts}, unique-id = {31814813}, abstract = {Ontology-based data integration (OBDA) plays a critical role in heterogeneous data integration, due to the excellent semantic interoperability and rigidly mathematical foundations of ontologies. However, the traditional methods for constructing ontology are manual, in which a lot of effort and experience from domain experts are required. Accordingly, ontology learning (OL) was proposed to (semi-)automatically construct ontologies, in which entities are usually extracted and mapped into the lower-dimensional vector space, thereby, the relations could be learned based on the computation and inference. The techniques of ontology learning are classified into four categories: association rule mining (ARM), formal concept analysis(FCA), inductive logic programming (ILP), neural networks(NN) and machine learning. However, the semantic collision will inevitably occur while learning and constructing ontologies from multi-source and heterogenous database (semi-)automatically. Consequently, it will induce the mismatching and inconsistency while mapping between source schema and target schema. To address the above issues, the semantic consistency behind ontology learning and schema mapping are investigated based on the formal representation language. Considering the semantic compatibility of OWL DL (description logic ontologies) and excellent expressivity of formal representation language, description logics(DLs) and W-graph are employed to formalize the process of ontology learning for (semi-)automatically constructing OWL DL. Furthermore, SOtags (Second-Order tuple-generating dependency tags) and database mapping graph are utilized to formalize the schema mapping for providing data-exchange between source schema and target schema, in which the semantics behind schema mapping is analyzed by introducing information fluxes. Moreover, the semantic consistency behind ontology learning and schema mapping are checked by using the model checking and ontology alignment. Besides, an example is presented to demonstrate the specific process of formalizing and checking the semantic consistency behind ontology learning and schema mapping for heterogeneous data integration.}, year = {2020}, pages = {115-115}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} } @inproceedings{MTMT:31206561, title = {Use of Ontology Learning in Information System Integration: A Literature Survey}, url = {https://m2.mtmt.hu/api/publication/31206561}, author = {Ma, Chuangtao and Molnár, Bálint}, booktitle = {Intelligent Information and Database Systems}, doi = {10.1007/978-981-15-3380-8_30}, unique-id = {31206561}, abstract = {Ontology-based information integration is a useful method to integrate heterogeneous data at the semantic level. However, there are some bottlenecks of the traditional method for constructing ontology, i.e., time-consuming, error-prone, and semantic loss. Ontology learning is a kind of ontology construction approach based on machine learning, it provides a new opportunity to tackle the above bottlenecks. Especially, it could be employed to construct ontologies and integrate large-scale and heterogeneous data from various information systems. This paper surveys the latest developments of ontology learning and highlights how they could be adopted and play a vital role in the integration of information systems. The recent techniques and tools of ontology learning from text and relational database are reviewed, the possibility of using ontology learning in information integration were discussed based on the mapping results of the aforementioned bottlenecks and features of ontology learning. The potential directions for using ontology learning in information systems integration were given.}, year = {2020}, pages = {342-353}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} } @inproceedings{MTMT:30787772, title = {Data Integration of Legacy ERP System Based on Ontology Learning from SQL Scripts}, url = {https://m2.mtmt.hu/api/publication/30787772}, author = {Ma, Chuangtao}, booktitle = {New Trends in Databases and Information Systems}, doi = {10.1007/978-3-030-30278-8_52}, unique-id = {30787772}, abstract = {To tackle the problem of low-efficiency integration of heterogeneous data from various legacy ERP systems, a data integration approach based on ontology learning are presented. Considering the unavailability of database interface and diversity of DBMS and naming conventions of legacy information systems, a data integration framework for legacy ERP systems based on ontology learning from structured query language (SQL) scripts (RDB) are proposed. The key steps and technicality of the proposed framework and the process of ontology-based semantic integration are depicted.}, year = {2019}, pages = {546-551}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579} } @inproceedings{MTMT:30679504, title = {A Legacy ERP System Integration Framework based on Ontology Learning}, url = {https://m2.mtmt.hu/api/publication/30679504}, author = {Ma, Chuangtao and Molnár, Bálint}, booktitle = {Proceedings of the 21st International Conference on Enterprise Information Systems}, doi = {10.5220/0007740602310237}, unique-id = {30679504}, abstract = {In the past decades, there are various legacy ERP systems that exist in different departments or suborganizations within the enterprise. The majority of the legacy ERP systems are heterogeneous systems, that may be developed by different software companies under different development framework, which create a big challenge for organizations to develop and implement centralized and integrated management systems based on their existing legacy ERP systems to respond the dynamic business environment with agility. Ontologies are viewed as an effective technology to integrate different data from multiple heterogeneous sources, the ontology learning methods were proposed to achieve (semi-)automated construction of ontologies. This paper proposes a general framework for legacy ERP system integration based on ontology learning to tackle this challenge. Initially, the related literature is reviewed from the perspective of system integration and ontology learning, then an integration framework based on ontology learning is given, and the basic workflow and ontology learning process are analysed and illustrated.}, year = {2019}, pages = {231-237}, orcid-numbers = {Ma, Chuangtao/0000-0002-6492-2579; Molnár, Bálint/0000-0001-5015-8883} }