Multi-document summarization

About: Multi-document summarization is a research topic. Over the lifetime, 2270 publications have been published within this topic receiving 71850 citations.

Multidocument summarization based on concept space

Abstract: Capturing relevant information is important in supporting decision making. We propose a new summarization method based on cluster analysis, concept space, and statistical approach to extract the essence from a collection of documents. A prototype system has been developed to condense a set of documents into a list of key issues and expands the key issues to form a summary. Cluster analysis and concept space was used as a bridge to connect convergent and divergent processes. Such approach reduces information loss due to vocabulary switching in the summarization process. In the divergent process, it selects the anchored sentences from the original documents to form a summary based on the concept terms generated previously. A user evaluation has been conducted for its usefulness and other performance indices. The results indicate that such approach is promising.

Context Based Topical Document Summarization

Abstract: A condition of information available on the web is getting increased day by day as a result leading to information overload. To find important and useful information is becoming difficult. This growth has created a huge demand for automatic methods and tools for text summarization. In the process of text summarization, text is reduced to meaningful small size. Sentences are extracted to build summary. summary will be effective when there will be more topical terms in it. So to summarize the text or in general for proper information retrieval term weighting schemes is very important. In this paper a review of various term weighting schemes and different summarization techniques is presented. Proposed context score based text summarization model is presented.

Source and Domain‐Specific Summarization

Abstract: From 1950–1970, research into automatic summarization essentially centered on documents with a general discourse, with two exceptions: Luhn’s pioneering experiments conducted on technical and scientific corpora [LUH 58] and Pollock & Zamora’s research into summarizing chemistry documents [POL 75]. In the 1990s, several researchers started to work on documents containing a specialized discourse, but as a general rule, the research used the same strategies as those used for summarizing documents with a general discourse. In this chapter, four automatic summarization systems for specialized documents will be presented. Yet Another CHemistry Summarizer (Yachs2) is dedicated to documents about organic chemistry; SummTerm is a system which uses semantic resources to generate summaries of medical articles. The third system is a summarizer combining statistical and linguistic algorithms, applied to the domain of biomedical articles. Finally, there is a summarization system for court decisions. With regard to source specific summarization, four systems oriented at summarizing online documents will be presented: web page summarization, microblog (tweet) summarization, email summarization and opinion summarization.

Tweet Contextualization: a Strategy Based on Document Retrieval Using Query Enrichment and Automatic Summarization.

Abstract: The aim of the tweet contextualization INEX (Initiative for the Evaluation of XML retrieval) task at CLEF 2013 (Conference and Labs of the Evaluation Forum) is to build a system that provides automatically information related with different tweets, that is, a summary that explains a specific tweet. In this article, our strategy and results are presented. The methodology for the task in English includes three stages. First, automatic reformulations of the initial queries provided for the task, that is, the tweets, are performed. In this research, we use words sequences that agree with the typical terminological patterns, name entities, hashtags and Twitter users accounts, since we consider that they are representative of tweets’ topics. Second, related documents are retrieved from Wikipedia with the search engine Indri, using the reformulated queries. Third, the obtained documents are summarized by using two different automatic summarization systems, in order to provide the final summary associated to each query. Regarding the pilot task for Spanish, our strategy includes a first stage where automatic reformulations of the initial queries provided for the task (similar to English) are carried out. However, it does not include neither the search engine Indri nor the summarization systems REG and Cortex. In this case, we directly extract relevant text passages from Wikipedia pages using the generated queries and we build the summary with the first sentences of these pages.

A pioneering tool for text summarization using star map

Abstract: Text Summarization is condensing the source text into a shorter version preserving its information content and overall meaning. It is very difficult for human beings to manually summarize large documents of text. The text summarization method consists of selecting important sentences, paragraphs etc. from the original document and converting them into a star map. The importance of sentences is decided based on statistical and linguistic features of sentences. A star map summarization method consists of understanding the original text and re-telling it in fewer words. This star map is used for duplicate elimination, exam paper evaluator, lesson planning, Identify Shingling. A Pioneering Tool For Text Summarization using Star Map has been presented.