IDENTIFICATION OF TEMPORAL EXPRESSIONS IN THE DOMAIN OF TOURISM

Abstract. This paper presents how an existing temporal processor was adapted to be used by the English Question Answering system developed part of the EU-funded project QALL-ME. Experiments applying the existing temporal processor to questions from the domain of tourism revealed that the existing temporal processor tackles far too many temporal expressions, and this makes it slower than necessary. In light of this, a simplified tem-poral processor which identifies only temporal expressions present in user questions was implemented. The two temporal annotators are evaluated on 1,118 randomly selected user questions and an error analysis is presented. 1