@conference {cFernandezf, title = {Enhancing Online Knowledge Graph Population with Semantic Knowledge}, booktitle = {19th International Semantic Web Conference (ISWC)}, year = {2020}, month = {11/2020}, address = {Virtual}, abstract = {

Knowledge Graphs (KG) are becoming essential to organize, represent and store the world{\textquoteright}s knowledge, but they still rely heavily on humanly-curated structured data. Information Extraction (IE) tasks, like disambiguating entities and relations from unstructured text, are key to automate KG population. However, Natural Language Processing (NLP) methods alone can not guarantee the validity of the facts extracted and may introduce erroneous information into the KG.\ This work presents an end-to-end system that combines Semantic Knowledge and Validation techniques with NLP methods, to provide KG population of novel facts from clustered news events.\ The contributions of this paper are two-fold: First, we present a novel method for including entity-type knowledge into a Relation Extraction model, improving F1-Score over the baseline with TACRED and TypeRE datasets. Second, we increase the precision by adding data validation on top of the Relation Extraction method. These two contributions are combined in an industrial pipeline for automatic KG population over aggregated news, demonstrating increased data validity when performing online learning from unstructured web data. Finally, the TypeRE and AggregatedNewsRE datasets build to benchmark these results are also published to foster future research in this field.

}, keywords = {Data Validation, Knowledge Graph, Relation Extraction}, author = {Fern{\`a}ndez, D{\`e}lia and Rimmek, Joan Marco and Espadaler, Joan and Garolera, Blai and Barja, Adri{\`a} and Codina, Marc and Sastre, Marc and Xavier Gir{\'o}-i-Nieto and Riveiro, Juan Carlos and Bou-Balust, Elisenda} }