In this paper, we propose a method to highlight the most important parts of documents, in order to help users to reach to their desired information in information space more beneficially. To do this, the results obtained from a multi-document cluster-based summarization system based upon different perspectives of summarization (such as query-based, general, etc.) are fused in a way that the fin...

Aiming at the difficulties in document-level summarization, this paper presents a two-stage, extractive and then abstractive summarization model. In first stage, we extract important sentences by combining similarity matrix (only used for time) or pseudo-title, which takes full account of features (such as sentence position, paragraph more.). To coarse-grained from document, considers different...

Summarization, an extremely important technique in Data Mining is an automatic learning technique aimed to extract the most valuable information from a large size document or the articles. The goal is to create the summary of the document, but substantially different from each other. Text Document summarization refers to the summarization of text documents based upon their content. The proposed...

We have developed a multilingual version of Columbia Newsblaster as a testbed for multilingual multi-document summarization. The system collects, clusters, and summarizes news documents from sources all over the world daily. It crawls news sites in many different countries, written in different languages, extracts the news text from the HTML pages, uses a variety of methods to translate the doc...

1.0 Introduction Much of the historical and current summarization literature has been technologycentered with the questions posed and answered having implications for technology development. Though commercial summarization products have appeared in the market place and developers continue to explore new summarization areas, few papers have been user-centered, examining summarization technology ...

Automatic summarization can help users extract the most important pieces of information from the vast amount of text digitized into electronic form everyday. Central to automatic summarization is the notion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for semantically aware representations of sentences as a basis for measuring si...

Update summarization is an extension of query-focused multidocument summarization which was launched at DUC 2007. The essential problem of update summarization is to attain the information novelty and topic continuity simultaneously. In this paper, we proposed several Temporal Content Filtering Methods to extract the time-varying information for the update summarization task, while the topic co...

Sentence Connectivity is a textual characteristic that may be incorporated intelligently for the selection of sentences of a well meaning summary. However, the existing summarization methods do not utilize its potential fully. The present paper introduces a novel method for singledocument text summarization. It poses the text summarization task as an optimization problem, and attempts to solve ...

Query-oriented summarization is primarily concerned with synthesizing an informative and well-organized summary from a document collection for a given query. In the existing summarization methods, each individual sentence in the document collection is represented as Bag of Words (BOW). In this paper, we propose a novel framework which improves query-oriented summarization via sentence wikificat...

The Text Analysis Conferences (TAC) offer a unique occasion to show innovative approaches to text summarization. As a first incursion into this new research area, LIPN participated in the following tasks of TAC 2008: the Update Summarization task and the Opinion Summarization task. LIPN systems obtained good results for Opinion Summarization; however, we are confident that there is room for imp...