Context-aware and multilingual information extraction for a tourist recommender system

We present information extraction for a semantic personalised tourist recommender system. The main challenges in this setting are that information is spread across various information sources, it is usually stored in proprietary formats and is available in different languages in varying degrees of accuracy. We address the mentioned challenges and describe our realization and ideas how to deal with each of them. In our paper we describe scraping and extracting keywords from different web portals with different languages, how we deal with missing multi-lingual data, and how we identify the same objects from different sources.