An Effective Approach for AESOP and Guided Summarization Task

In this paper we, present an (1) unsupervised system for AESOP task and (2) a generic multi-document summarization system for guided summarization task. In devised systems we give emphasis on (1) roll & importance of words and sentences in document, (2) number & coverage strength of topics. Next we exploit the statistical features, simple heuristics and grammatical facts to capture important facts and information flow in document. Thus our devised system collects useful information from source or model summaries and uses it for evaluation of target summaries. Similarly it collects useful information from given text and use it for summarization. We believe that output of a good generic system may be able to answer the most of the general queries, which are used in guided summarization task. This is the main reason of development of a generic multi-document summarization system for guided summarization task. Part-1: AESOP Task

[1]  John M. Conroy,et al.  Mind the Gap: Dangers of Divorcing Evaluations of Summary Content from Linguistic Quality , 2008, COLING.

[2]  Jun-ichi Fukumoto,et al.  Automated Summarization Evaluation with Basic Elements. , 2006, LREC.

[3]  Eduard Hovy,et al.  Evaluating DUC 2005 using Basic Elements , 2005 .

[4]  Li Su.  Research on Maximum Entropy Model for Keyword Indexing , 2004 .

[5]  Ani Nenkova,et al.  Evaluating Content Selection in Summarization: The Pyramid Method , 2004, NAACL.

[6]  Ani Nenkova,et al.  The Pyramid Method: Incorporating human content selection variation in summarization evaluation , 2007, TSLP.

[7]  M. Newman,et al.  Finding community structure in very large networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Hans van Halteren,et al.  Evaluating Information Content by Factoid Analysis: Human annotation and stability , 2004, EMNLP.

[9]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[10]  Robert L. Donaway,et al.  A Comparison of Rankings Produced by Summarization Evaluation Measures , 2000 .

[11]  K. Srinathan,et al.  Evaluating Information Coverage in Machine Generated Summary and Variable Length Documents , 2010, COMAD.

[12]  K. Srinathan,et al.  Automatic keyphrase extraction from scientific documents using N-gram filtration technique , 2008, ACM Symposium on Document Engineering.

[13]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.