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.

Reader-Aware Multi-Document Summarization: An Enhanced Model and The First Dataset

Abstract: We investigate the problem of reader-aware multi-document summarization (RA-MDS) and introduce a new dataset for this problem. To tackle RA-MDS, we extend a variational auto-encodes (VAEs) based MDS framework by jointly considering news documents and reader comments. To conduct evaluation for summarization performance, we prepare a new dataset. We describe the methods for data collection, aspect annotation, and summary writing as well as scrutinizing by experts. Experimental results show that reader comments can improve the summarization performance, which also demonstrates the usefulness of the proposed dataset.

A Study on Video Summarization Techniques

Abstract: The paper covers study of various techniques for key frames based video summarization available in the literature. There have been tremendous needs of video processing applications to deal with abundantly available & accessible videos. One of the research areas of interest is Video Summarization that aims creating summary of video to enable a quick browsing of a collection of large video database. It is also useful for allied video processing applications like video indexing, retrieval etc. Video Summarization is a process of creating & presenting a meaningful abstract view of entire video within a short period of time. Mainly two types of video summarization techniques are available in the literature, viz. key frame based and video skimming. For key frame based video summarization, selection of key frames plays important role for effective, meaningful and efficient summarizing process.

Improving text summarization using neuro-fuzzy approach

Abstract: In today’s digital era, it becomes a challenge for netizens to find specific information on the internet. Many web-based documents are retrieved and it is not easy to digest all the retrieved infor...

A new approach for multi-document update summarization

Abstract: Fast changing knowledge on the Internet can be acquired more efficiently with the help of automatic document summarization and updating techniques. This paper describes a novel approach for multi-document update summarization. The best summary is defined to be the one which has the minimum information distance to the entire document set. The best update summary has the minimum conditional information distance to a document cluster given that a prior document cluster has already been read. Experiments on the DUC/TAC 2007 to 2009 datasets (http://duc.nist.gov/, http://www.nist.gov/tac/) have proved that our method closely correlates with the human summaries and outperforms other programs such as LexRank in many categories under the ROUGE evaluation criterion.

Improving graph based multidocument text summarization using an enhanced sentence similarity measure

Abstract: Multi document summarization is a process to produce a single summary from a set of related documents collected from heterogeneous sources. Since the documents may contain redundant information, the performance of a multi document summarization system heavily depends on the sentence similarity measure used for removing redundant sentences from the summary. For graph based multi document summarization where existence of an edge between a pair of sentences is determined based on how much two sentences are similar to each other, the sentence similarity measure also plays an important role. This paper presents an enhanced method for computing sentence similarity aiming for improving multidocument summarization performance. Experiments using two different datasets show the effectiveness of the proposed sentence similarity measure in improving the performance of a graph based multidocument summarization system.