Can You Summarize This? Identifying Correlates of Input Difficulty for Multi-Document Summarization
نویسندگان
چکیده
Different summarization requirements could make the writing of a good summary more difficult, or easier. Summary length and the characteristics of the input are such constraints influencing the quality of a potential summary. In this paper we report the results of a quantitative analysis on data from large-scale evaluations of multi-document summarization, empirically confirming this hypothesis. We further show that features measuring the cohesiveness of the input are highly correlated with eventual summary quality and that it is possible to use these as features to predict the difficulty of new, unseen, summarization inputs.
منابع مشابه
Can You Summarize This? Identifying Correlates of Input Difficulty for Generic Multi-Document Summarization
Different summarization requirements could make the writing of a good summarymore difficult, or easier. Summary length and the characteristics of the input are such constraints influencing the quality of a potential summary. In this paper we report the results of a quantitative analysis on data from large-scale evaluations of multi-document summarization, empirically confirming this hypothesis....
متن کاملA survey on Automatic Text Summarization
Text summarization endeavors to produce a summary version of a text, while maintaining the original ideas. The textual content on the web, in particular, is growing at an exponential rate. The ability to decipher through such massive amount of data, in order to extract the useful information, is a major undertaking and requires an automatic mechanism to aid with the extant repository of informa...
متن کاملAn Integrated Multi-document Summarization Approach based on Word Hierarchical Representation
This paper introduces a novel hierarchical summarization approach for automatic multidocument summarization. By creating a hierarchical representation of the words in the input document set, the proposed approach is able to incorporate various objectives of multidocument summarization through an integrated framework. The evaluation is conducted on the DUC 2007 data set.
متن کاملTelugu - English Dictionary Based Cross Language Query Focused Multi-Document Summarization
Summarization systems and Question Answering systems can be treated to have complementary functionality to each other. For instance, a question answering system could have a summarization module, that can summarize the fragments of answers found by the question answering system. On the other hand a summarization system can be given a question as input, to generate a question focused summary as ...
متن کاملA Survey of Generating Multi-Document Summarizations
Summarization is a Process of filtering the most important information from source/sources for a particular user and task. Summarization is a very useful task which gives support to many other tasks. It takes advantage of the techniques developed for Natural Language Processing tasks. Multidocument summarization is a technique of summarize the multiple document into one paragraph. Multi-documen...
متن کامل