Topic
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.
Papers published on a yearly basis
Papers
More filters
Proceedings Article•
19 Nov 2016TL;DR: A method for detecting salient, keys ences from stories that discuss the same topic by using the TF-IDF term weighting method and adapting stock market trend analysis technique, i.e., Moving Average Convergence Divergence (MACD).
Abstract: This paper focuses on continuous news streams and presents a method for detecting salient, keys ences from stories that discuss the same topic. Our hypothesis about key sentences in multiple stories is that they include words related to the target topic, and thesub jectof a story. In addition to the TF-IDF term weighting method, we used the result of assigning domain-specific senses to each word in the story to identify a subject. A topic, on the other hand, is identified by using a model of ”topic dynamics”. We defined a burst as a time interval of maximal length over which the rate of change is positive acceleration. We adapted stock market trend analysis technique, i.e., Moving Average Convergence Divergence (MACD). It shows the relationship between two moving averages of prices, and is popular indicator of trends in dynamic marketplaces. We utilized it to measure topic dynamics. The method was tested on the TDT corpora, and the results showed the effectiveness of the method.
Journal Article•
TL;DR: The solution to be discussed is about to use Automatic Method for summarization, a way to generate a text, which contains the important portion of information of the original text or texts.
Abstract: In today's world there are huge amount of data is available on Internet. Everyone is used to with retrieval of this data/info from different sites, applications in direct or indirect way. Many times it is necessary to summarize the articles or documents in short but also important format. Summarization via manual method is an older technique. Each human may have different summary however, some important aspect of text is always present in everyone's summary. In practical, humans have limitations of speed and time. It reduces the performance as per time of work and time of input articles are increasing. It is pretty good if same is done by Computer which has intelligence! Text Summarization is a way to generate a text, which contains the important portion of information of the original text or texts. Several techniques are generated depending upon many parameters to find the summary as the type, position and format of the sentences in an input text, formats of different words occurrence of a particular word in a text etc. The solution to be discussed is about to use Automatic Method for summarization.
29 Oct 2007
TL;DR: This paper proposes to build two rankers based SVR model each of which adopts a set of features and designs a combination strategy to acquire the sentences which can satisfy both the query focus and the documents' focus.
Abstract: Most up-to-date multi-document summarization systems are built upon the extractive framework, which score and rank the sentences based on the associated features. Generally these features can be classified into two sets: query-dependent features and query-independent features. Query-dependent features are selected for satisfying the topic queries while the query-independent features are for the documents' focus. In this paper, we propose to build two rankers based SVR model each of which adopts a set of features. Then we design a combination strategy to acquire the sentences which can satisfy both the query focus and the documents' focus. The evaluations by ROUGE criteria on DUC 2006 and 2007 document sets demonstrate the competability and the adaptability of the proposed approaches.
01 Jan 2013
TL;DR: Automatic Text Summarization is the Process in which the input is to the computer is the text, whereas the output is the concise extract of the input data.
Abstract: Availability of ample of data on the web is difficult of access. Hence it has become an important research area of automatic text summarization within the Natural Language processing. Text mining is another important research field that brings meaning to the natural language on the web. Automatic Text Summarization is the Process in which the input is to the computer is the text, whereas the output is the concise extract of the input data. The entire process of automatic text summarization takes four stages. They are tokenization, feature identification, characterization, tagging and summarization. The work can be used in much practical application.
TL;DR: Zhang et al. as discussed by the authors proposed a topic-aware graph-based neural interest summarization method (UGraphNet), enhancing user semantic mining by unearthing potential user relations and jointly learning the latent topic representations of posts that facilitates user interest learning.
Abstract: User-generated content is daily produced in social media, as such user interest summarization is critical to distill salient information from massive information. While the interested messages (e.g., tags or posts) from a single user are usually sparse becoming a bottleneck for existing methods, we propose a topic-aware graph-based neural interest summarization method (UGraphNet), enhancing user semantic mining by unearthing potential user relations and jointly learning the latent topic representations of posts that facilitates user interest learning. Experiments on two datasets collected from well-known social media platforms demonstrate the superior performance of our model in the tasks of user interest summarization and item recommendation. Further discussions also show that exploiting the latent topic representations and user relations are conductive to the user automatic language understanding.