Evaluating approaches for supervised semantic labeling
This work addresses the challenge of semantic labeling for data integration in enterprise or web domains, but it appears incremental as it builds on existing classification frameworks.
The paper tackles the problem of semantic labeling of relational schemas by mapping attributes to ontology classes and properties, formulating it as a multi-class classification task. It develops new machine learning and deep learning models that address issues like class imbalance and lack of labeled data, and evaluates them against state-of-the-art approaches.
Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic description. A common ontology provides a way to represent the meaning of a relational schema and can facilitate the integration of heterogeneous data sources within a domain. Semantic labeling is achieved by mapping attributes from the data sources to the classes and properties in the ontology. We formulate this problem as a multi-class classification problem where previously labeled data sources are used to learn rules for labeling new data sources. The majority of existing approaches for semantic labeling have focused on data integration challenges such as naming conflicts and semantic heterogeneity. In addition, machine learning approaches typically have issues around class imbalance, lack of labeled instances and relative importance of attributes. To address these issues, we develop a new machine learning model with engineered features as well as two deep learning models which do not require extensive feature engineering. We evaluate our new approaches with the state-of-the-art.