While authoring content, users can benefit from being able to provide citations and to verify statements that include facts. This disclosure describes techniques described to provide citations and/or corrections for user text, e.g., in a document, within an authoring application. Trained machine learning models are used to generate a feature vector based on user text which is matched to feature vectors of known information sources. Citations and corrections are provided based on identifying reliable sources such as academic publications, reliable news sources, etc. along with a visual indicator of the quality of the source.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Gonnet, Pedro and Cărbune, Victor, "Automatic identification and ranking of knowledge sources", Technical Disclosure Commons, (December 04, 2017)