RuTaBERT is a framework for solving column type and property annotation problems based on fine-tuning a pre-trained language model (e.g., BERT) using a large-scale corpus of Russian-language tables.

CoLeM framework is a table model based on contrastive learning techniques for solving the problem of Column Type Annotation.

Dataset from the authors of RuTaBERT and is based on the Russian Web Tables. Only relational tables were chosen from Russian Web Tables with headers matching their selected 170 DBpedia semantic types.