DOCTORAL ABSTRACT Automatic Summarization Focusing on Document Genre and Text Structure Yohei Seki , ¡ Department of Informatics, The Graduate University for Advanced Studies (Sokendai) National Institute of Informatics (NII) ¡ Tokyo 101-8430, Japan seki@nii.ac.jp Advisor: Noriko Kando This dissertation proposes a new automatic summarization method focusing on document genre and text structure, and veri es its e ectiveness. Document genre refers to the type of document, such as a diary or a report. Text structure refers to the functional aspects of the text and divides the text into sentence units or components, according to their functional roles. This type of structure includes both the components and their organization within the text of a speci c document genre. We used text structure and document genre to extract important sentences from source documents and to generate output summaries. To date, automatic summarization research has focused principally on the topic of the document, using term frequency as a clue. The problem with this approach is that the resulting output summary lacks coherence and balance and does not di erentiate between types of information. For example, sometimes the user is looking for facts concerning a certain topic, while at
/lp/association-for-computing-machinery/automatic-summarization-focusing-on-document-genre-and-text-structure-A8dIli440J