Abstract Besides the problems of topic relevance and information diversity tackled by traditional topic-focused multi-document summarization, the update summarization is required to address the problem of information novelty as well. In this paper, HeatSum, an extractive approach based on heat conduction for update summarization, is proposed. The process can naturally make use of the relationships among the given topic, the old sentences, the new sentences, and the sentences selected and to be selected to find proper sentences for update summarization. Therefore, HeatSum is able to simultaneously address the challenging problems above for update summarization in a unified way. The experiments on benchmark of TAC2009 are performed and the ROUGE evaluation results show that the HeatSum achieves fine performance compared to the best existing performing systems in TAC tasks and it significantly outperforms other baseline methods.
[1] Boudin F,El-Bμèze M,Torres-Moreno J M.A Scalable MMR Approach to Sentence Scoring for Multi-Document Update Summarization // Proc of the 22nd International Conference on Computing Linguistics.Manchester,UK,2008: 23-26 [2] Wan Xiaojun.Timedtextrank: Adding the Temporal Dimension to Multi-Document Summarization // Proc of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.Amsterdam,Netherlands,2007: 867-868 [3] Zhang Jin,Cheng Xueqi,Xu Hongbo,et al.ICTCASs ICTGrasper at TAC 2008: Summarizing Dynamic Information with Signature Terms Based Content Filtering [EB/OL].[2010-08-13].http://www.nist.gov/tac/publications/2008/participant.papers/ICTCAS.proceedings.pdf [4] Steinberger J,Jeek K.Update Summarization Based on Novel Topic Distribution // Proc of the 9th ACM Symposium on Document Engineering.Munich,Germany,2009: 205-213 [5] Li Wenjie,Wei Furu,Lu Qin,et al.PNR 2: Ranking Sentences with Positive and Negative Reinforcement for Query-Oriented Update Summarization // Proc of the 22nd International Conference on Computational Linguistics.Manchester,UK,2008: 489-496 [6] Erkan G,Radev D R.LexRank: Graph-Based Lexical Centrality as Salience in Text Summarization.Journal of Artificial Intelligence Research,2004,22(1): 457-479 [7] Lin C Y,Hovy E.Manual and Automatic Evaluation of Summaries // Proc of the ACL-02 Workshop on Automatic Summarization.Morristown,USA,2002: 45-51 [8] Mihalcea R,Tarau P.Textrank: Bringing Order into Texts // Proc of the Conference on Empirical Methods in Natural Language Processing.Barcelona,Spain,2004: 404-411 [9] Otterbacher J,Erkan G,Radev D.Using Random Walks for Question-Focused Sentence Retrieval // Proc of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing.Vancouver,Canada,2005: 915-922 [10] Saggion H,Bontcheva K,Cunningham H.Robust Generic and Query-Based Summarization // Proc of the 10th Conference on European Chapter of the Association for Computational Linguistics.Stroudsburg,USA,2003: 235-238 [11] Wan Xiaojun,Yang Jianwu,Xiao Jianguo.Manifold-Ranking Based Topic-Focused Multi-Document Summarization // Proc of the 20th International Joint Conference on Artificial Intelligence.Hyderabad,India,2007: 2903-2908 [12] Wei Furu,Li Wenjie,Lu Qin,et al.Query-Sensitive Mutual Reinforcement Chain and Its Application in Query-Oriented Multi-Document Summarization // Proc of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.Singapore,Singapore,2008: 283-290 [13] Zhang Jin,Cheng Xueqi,Wu Gaowei,et al.Adasum: An Adaptive Model for Summarization // Proc of the 17th ACM Conference on Information and Knowledge Management.Napa Valley,USA,2008: 901-910 [14] Conroy J M,Schlesinger J D.Classy Query-Based Multidocument Summarization [EB/OL].[2010-08-13].http://www.nlpic.nist.gov/tac/projects/duc/pubs/2005papers/ida.conroy.pdf [15] Hovy E,Lin C Y,Zhou L,et al.Automated Summarization Evaluation with Basic Elements // Proc of the 5th Conference on Language Resources and Evaluation.Genvoa,Italy,2006: 899-902 [16] Allan J,Gupta R,Khandelwal V.Temporal Summaries of New Topics // Proc of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.New Orleans,USA,2001: 10-18 [17] Carbonell J,Goldstein J.The Use of MMR,Diversity-Based Reranking for Reordering Documents and Producing Summaries // Proc of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.Melbourne,Australia,1998: 335-336 [18] Zhou Tao,Kuscsik Z,Liu Jianguo,et al.Solving the Apparent Diversity-Accuracy Dilemma of Recommender Systems.Proc of the National Academy of Sciences of the United States of America,2010,107(10): 4511-4515 [19] Zhang Zike,Zhou Tao,Zhang Yicheng.Personalized Recommendation via Integrated Diffusion on User-Item-Tag Tripartite Graphs.Physica A: Statistical Mechanics and Its Applications,2010,389(1): 179-186 [20] Zhang Y C,Blattner M,Yu Y K.Heat Conduction Process on Community Networks as a Recommendation Model.Physical Review Letters,2007,99(15): 154301 [21] Korniss G,Hastings M,Bassler K,et al.Scaling in Small-World Resistor Networks.Physics Letters A,2006,35(5/6): 324-330 [22] Wu F Y.Theory of Resistor Networks: The Two-Point Resistance.Journal of Physics A: Mathematical and General,2004,37(26): 6653-6673 [23] Lin C Y.Rouge: A Package for Automatic Evaluation of Summaries // Proc of the ACL-04 Workshop on Text Meaning and Interpretation.Barcelona,Spain,2004: 74-81 [24] Long Chong,Huang Minlie,Zhu Xiaoyan.Tsinghua University at TAC 2009: Summarizing Multi-Documents by Information Distance [EB/OL].[2010-08-13].http://www.nist.gov/tac/publications/2009/participant.paper/THVSVM.proceedings.pdf [25] Dang H T,Owczarzak K.Overview of the Tac 2009 Summarization Track (draft) [EB/OL].[2010-08-13].http://www.nist.gov/publications/2009/presentations/TAC2009_Sum_overview.pdf
2012, Vol. 25 
