Named Entity Disambiguation in a Question Answering System

In this paper, we describe how we use a named entity disambiguation module to merge entities in a question answering system. The question answering system uses a baseline passage retrieval component that extracts paragraphs from the Swedish version of Wikipedia. The passages are indexed and ranked using the Lucene platform. Prior to the indexing, we carried out a recognition and disambiguation of the named entities. We used the Stagger part-of-speech tagger to tag the documents and we implemented a disambiguation module. We extracted and merged the answer candidates using their wikidata Q-number. This enables the question-answering system to benefit from the synonymy facility of Wikipedia as well as an extended set of properties.