Analysis of Multi-Document Viewpoint Summarization Using Multi-Dimensional Genres

An interactive information retrieval system that provides different types of summaries of retrieved documents according to each user’s information needs can be effective for understanding the contents. The purpose of this study is to build a multi-document summarizer to produce summaries according to such viewpoints. As an exploratory stage of investigation, we examined the effectiveness of genre for source documents to produce different types of summaries. Once a set of documents on a topic is provided to our summarization system, a list of topics discussed in the given document set is presented, so that the user can select a topic of interest from the list as well as the summary type, such as opinion-oriented, fact-reporting or knowledge-focused, according to their requirements. We assume a relationship between a summary type and human recognition of information types included in the source: a document genre. We also analyzed the results of the multidocument summarization using automatic genre classification to reveal the association between genre dimensions and the summary types.