This repository provides data and scripts to use Sherlock, a DL-based model for semantic data type detection: https://sherlock.media.mit.edu.

Entity linking, entity typing and relation extraction: Matching CSV to a Wikibase instance (e.g., Wikidata) via Meta-lookup

Implementation of algorithms for semantic table implementation, including the TableMiner+ method

RuTaBERT is a model solving the problem of Column Type Annotation with pre-trained large language model (BERT), trained on the Russian corpus.

A web-based application for semantic table interpretation (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.

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

Large Language Model for Semantic Table Interpretation

semantic tableau is method of finding whether the given logic (propositional logic here) is consistent or inconsistent, whether it is valid (tautology) or not.