Departmental Papers (CIS)

Date of this Version


Document Type

Conference Paper


Nenkova, A. & Louis, A., Can You Summarize This? Identifying Correlates of Input Difficulty for Generic Multi-Document Summarization, 46th Annual Meeting of the Association for Computational Linguistics, June 2008, doi: anthology/P08-1094


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. 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.



Date Posted: 31 July 2012