Automatic Detection of Quotations in Multilingual News

Abstract

We present fully functional software that identifies direct speech quotations as part of its automatic analysis of more than 20,000 news articles per day in currently 10 languages. The system currently identifies over 2600 quotations per day, together with the person who made the quotation and – where applicable – the persons or organisations mentioned in the quotation. The most recent quotations from and about each person are listed on this person’s information page, which is updated daily. As another component of the system also identifies variants of each name, the quotes can be assigned to the same person even if his or her name is spelled differently, allowing users to view all quotations from or about any of the currently 640,000 person names in the system’s database in any of these languages. This automatic news analysis system is publicly accessible at http://press.jrc.it/NewsExplorer/.