Improving Diversity of Focused Summaries through the Negative Endorsements of Redundant Facts

We present NegativeRank, a novel graph-based sentence ranking model to improve the diversity of focused summary by performing random walks over sentence graph with negative edge weights. Unlike the typical eigenvector centrality ranking, our method models the redundancy among sentence nodes as the negative edges. The negative edges can be thought of as the propagation of disapproval votes which can be used to penalize redundant sentences. As the iterative process continues, the initial ranking score of a given node will be adjusted according to a long-term negative endorsement from other sentence nodes. The evaluation results confirm that our proposed method is very effective in improving the diversity of the focused summary, compared to several well-known text summarization methods.

[1]  Paul Van Dooren,et al.  The PageTrust Algorithm: How to rank web pages when negative links are allowed? , 2008, SDM.

[2]  Jade Goldstein-Stewart,et al.  The use of MMR, diversity-based reranking for reordering documents and producing summaries , 1998, SIGIR '98.

[3]  Ani Nenkova,et al.  The Impact of Frequency on Summarization , 2005 .

[4]  Xin Chen,et al.  Using negative voting to diversify answers in non-factoid question answering , 2009, CIKM.

[5]  Dragomir R. Radev,et al.  LexPageRank: Prestige in Multi-Document Text Summarization , 2004, EMNLP.

[6]  Sreenivas Gollapudi,et al.  Diversifying search results , 2009, WSDM '09.

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

[8]  Xiaojin Zhu,et al.  Improving Diversity in Ranking using Absorbing Random Walks , 2007, NAACL.

[9]  Zhiyong Lu,et al.  Summarizing Documents by Measuring the Importance of a Subset of Vertices within a Graph , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[10]  Christopher C. Yang,et al.  Addressing the Variability of Natural Language Expression in Sentence Similarity with Semantic Structure of the Sentences , 2009, PAKDD.

[11]  Fakhri Karray,et al.  A concept-based model for enhancing text categorization , 2007, KDD '07.

[12]  Eduard H. Hovy,et al.  Summarization Evaluation Using Transformed Basic Elements , 2008, TAC.

[13]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[14]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[15]  Simone Paolo Ponzetto,et al.  Knowledge Derived From Wikipedia For Computing Semantic Relatedness , 2007, J. Artif. Intell. Res..

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

[17]  Daniel Jurafsky,et al.  Shallow Semantic Parsing using Support Vector Machines , 2004, NAACL.

[18]  Lisa F. Rau,et al.  Automatic Condensation of Electronic Publications by Sentence Selection , 1995, Inf. Process. Manag..

[19]  Charles L. A. Clarke,et al.  Novelty and diversity in information retrieval evaluation , 2008, SIGIR '08.

[20]  Dragomir R. Radev,et al.  Using Random Walks for Question-focused Sentence Retrieval , 2005, HLT.

[21]  Chris H. Q. Ding,et al.  Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization , 2008, SIGIR '08.

[22]  Yong Yu,et al.  Enhancing diversity, coverage and balance for summarization through structure learning , 2009, WWW '09.

[23]  Ted Pedersen,et al.  Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

[24]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[25]  Jie Tang,et al.  Multi-topic Based Query-Oriented Summarization , 2009, SDM.

[26]  Christian Bauckhage,et al.  The slashdot zoo: mining a social network with negative edges , 2009, WWW.

[27]  Xiaojun Wan,et al.  Using Cross-Document Random Walks for Topic-Focused Multi-Document , 2006, 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06).

[28]  James Allan,et al.  Retrieval and novelty detection at the sentence level , 2003, SIGIR.