In this paper, we describe the following two approaches to summarization: (1) only sentence extraction, (2) sentence extraction + bunsetsu elimination. For both approaches, we use the machine learning algorithm called Support Vector Machines. We participated in both Task-A (single-document summarization task) and Task-B (multi-document summarization task) of TSC-2.

After lying dormant for over two decades, automated text summarization has experienced a tremendous resurgence of interest in the past few years. Research is being conducted in China, Europe, Japan, and North America, and industry has brought to market more than 30 summarization systems; most recently, a series of large-scale text summarization evaluations, Document Understanding Conference (DU...

Abstract We have introduced information extraction technique such as named entity tagging and pattern discovery to a summarization system based on sentence extraction technique, and evaluated the performance in the Document Understanding Conference 2001 (DUC-2001). We participated in the Single Document Summarization task in DUC-2001 and achieved one of the best performance in subjective evalua...

This is the first time we participate in TAC. In this report, we present our extractive summarization system on both initial and update summarization tracks of TAC 2010. We introduce an integrated method to generate all summaries. The TAC evaluation of results show that our summarization method is feasible but it has to be improved in future.

Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the summarization strategies. This novel framework for summarization has the advantage of producing highly responsive summaries, as indicated by the evaluation results. 2007 Elsevier Ltd. All rights ...

This Ph.D. thesis is the result of several years of research on automatic text summarization. Three major contributions are presented in the form of published and yet to be published papers. They follow a path that moves away from extractive summarization and toward abstractive summarization. The first article describes the HexTac experiment, which was conducted to evaluate the performance of h...

There are three unique cognitive mechanisms during note taking: generative processing, summarization, and sustained attention. Generative processing is active construction of associations between novel information prior knowledge experiences. Summarization forces identification the most pertinent to create a coherent synopsis. Sustained attention selectively concentrating on while ignoring irre...

Many natural language processing models are perceived to be fragile on adversarial attacks. Recent work attack has demonstrated a high success rate sentiment analysis as well classification models. However, attacks summarization have not been studied. Summarization tasks rarely influenced by word substitution, since advanced abstractive summary utilize sentence level information. In this paper,...

This paper describes the followed methodology to automatically generate titles for a corpus of questions that belong to sociological opinion polls. Titles for questions have a twofold function: (1) they are the input of user searches and (2) they inform about the whole contents of the question and possible answer options. Thus, generation of titles can be considered as a case of automatic summa...

The increasing availability of large-scale network data makes the problem of network summarization especially relevant. In any data summarization, however, it is important to remain aware of the information not being presented. As such, we present a mathematical framework within which to consider the problem of network summarization. Using that framework, the concept of information entropy is a...