Knowledge graphs are labeled and directed multi-graphs that encode information in the form of entities and relationships. They are gaining attention in different areas of computer science: from the improvement of search engines to the development of virtual personal assistants. Currently, an open challenge in building large-scale knowledge graphs from structured data available on the Web (HTML tables, CSVs, JSONs) is the semantic integration of heterogeneous data sources.
Rigorous evaluations and analyses of evaluation results are key towards improving Named Entity Linking systems. Nevertheless, most current evaluation tools are focused on benchmarking and comparative evaluations. Therefore, they only provide aggregated statistics such as precision, recall and F1-measure to assess system performance and no means for conducting detailed analyses up to the level of individual annotations.
Automatic Term Extraction is a fundamental Natural Language Processing task often used in many knowledge acquisition pro- cesses. It is a challenging NLP task due to its high domain dependence: no existing methods can consistently outperform others in all domains, and good ATE is very much an unsolved problem. We propose a generic method for improving the ranking of terms extracted by a potentially wide range of existing ATE methods.