Ontology matching is usually performed to find semantic correspondences between the entity elements of different ontologies to enable interoperability. Current research on ontology matching has largely focused on representation learning. However, there still exist two limitations. Firstly, they are only used in the element level matching phase, ignoring relations of the entity. Secondly, the final alignment threshold is usually determined manually within these methods. It is difficult for an expert to adjust the threshold value and even more for non-expert user. To address these issues, we propose an alternative ontology matching framework, which models the matching process by embedding techniques with jointly encoding ontology terminological description and network structure. We further improve our iterative final alignment method by introducing an automatic adjustment of threshold method. Finally, we perform an experimental evaluation and compare it with state-of-the-art ontology matching systems on four Ontology Alignment Evaluation Initiative (OAEI) datasets. Our approach performs better than most of the systems and achieves a competitive performance. Moreover, we obtained F-measure values of 93.8% and 90.8% on the OAEI Large Biomedical Ontologies FMA-NCI and FMA-SNOMED subtasks.