Exploitation of Named Entities in Automatic Text Summarization for Swedish

Background The technique of automatic text summarization has been developed for many years (Luhn 1959, Edmundson 1969 and Salton 1989). One way to do text summarization is by text extraction, which means to extract pieces of an original text on a statistical basis or with heuristic methods and put them together to a new shorter text with as much information as possible preserved (Mani & Maybury 1999). One important task in text extraction is topic identification. There are many methods to perform topic identification (see Lin & Hovy 1997). One is word counting at concept level that is more advanced than just simple word counting; another is identification of cue phrases to find the topic. Named Entity recognition is the task of finding and classifying proper nouns in running text. Proper nouns, such as names of persons and places, are often central in news reports. Therefore we have integrated a Named Entity tagger with our existing summarizer, SweSum, in order to study its effect on the resulting summaries.