Piek Vossen

Professor Computational Lexicology VU University Amsterdam

Piek Vossen (1960) is currently fulltime Professor Computational Lexicology at the Faculty of Arts, department Language, Cognition and Communication (LCC) at the Vrije Universiteit Amsterdam. He is the head of the Computational Lexicology & Terminology Lab (CLTL), Spinoza? laureate 2013, Founder and President of the Global WordNet Assocation (GWA) and member of the Koninklijke Hollandsche Maatschappij der Wetenschappen (KHMW). Vossen has published more than 200 (peer reviewed) articles in national and international journals, conference proceedings, book chapters and (hand)books. He has given invited lectures at several conferences and other occasions, is a regular organisor of and referee for (inter)national conferences and journals, and has served on several program committees and organizing committees of workshops and conferences. Piek Vossen studied Dutch and General Linguistics at the University of Amsterdam. In 1995, he received his PhD (cum laude) in Linguistics on Computational Lexicology and Lexicography. He has been involved in the following (EC?)projects: Links, Acquilex?I and II, Sift,EuroWordNet I and II, Meaning, Euroterm, Balkanet and Pidgin, Cornetto, DutchSemCor, Text to Political Positions, Semantics of History, Kyoto, BiographyNet, OpeNER, and NewsReader.

Talk Title: 
NewsReader: recording history by processing massive streams of daily news
Talk Abstract: 

The European NewsReader project develops a 'history recorder' to process daily streams of news in 4 language (English, Spanish, Italian and Dutch) to determine what happened, where and when in the world, and who was involved. The program uses the same strategy as humans to merge news with previously stored information, creating a longer-term history rather than storing separate events. Like humans, the program removes duplicate information and complements incomplete information while 'reading'. The result is a single story-line for all the events. Unlike humans, NewsReader will not forget any detail, will be able to recall the complete story as it was told, know who told what part of the story, and identify what sources contradict each other. Since it keeps track of all the original sources of information, the history recorder can also provide insights into how the story was told. This will tell us about the different perspectives from which different media sources present the news, both the news of today and the news of the past. The European project “NewsReader” is a collaboration of three European research groups and three companies, LexisNexis, ScraperWiki and Synerscope. The project started on January 2013 and will last 3 years. NewsReader will be tested on economic-financial news and on events relevant for political and financial decision-makers. About 25% of the news is about finance and economy. LexisNexis estimates the total volume of daily news items for this domain on about five-hundred-thousand.

Slideshare Presentation: