Information Extraction for Standardization of Tourism Products

Tourism product descriptions are strongly supported on natural language expressions. Appropriate offer selection, according to tourist needs, depends highly on how these are communicated. Since no human interaction is available while presenting tourism products online, the way these are presented, even when using only textual information, is a key success factor for tourism web sites to achieve a purchase. Due to the large amount of tourism offers and the high dynamics in this sector, manual data management is not a reliable or a scalable solution. This paper presents a prototype developed for automatic extraction of relevant knowledge from tourism-related natural language texts. Captured knowledge is represented in a normalized format and new textual descriptions are produced according to available marketing channels. At this phase, the prototype is focused on hotel descriptions and is already using real operational data retrieved from the KEYforTravel tourism platform.