Topic-Focused Summarization of News Events Based on Biased Snippet Extraction and Selection

详细信息    查看全文

• 作者：Pingping Lin (22) (23)
  Shize Xu (22) (23)
  Yan Zhang (22) (23)
  
• 关键词：Topic ; focused summarization ; Snippet ; Topic signature
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8870
• 期：1
• 页码：24-35
• 全文大小：477 KB
• 参考文献：1. Bollegala, D., Okazaki, N., Ishizuka, M.: A bottom-up approach to sentence ordering for multi-document summarization. Information Processing & Management聽46(1), 89鈥?09 (2010) CrossRef
  2. Boudin, F., Morin, E., et al.: Keyphrase extraction for n-best reranking in multi-sentence compression. In: Proccedings of the NAACL HLT 2013 Conference (2013)
  3. Castella, Q., Sutton, C.: Word storms: Multiples of word clouds for visual comparison of documents. arXiv preprint arXiv:1301.0503 (2013)
  4. Christensen, J., Mausam, S.S., Etzioni, O.: Towards coherent multi-document summarization. In: Proceedings of NAACL-HLT, pp. 1163鈥?173 (2013)
  5. D铆az, A., Gerv谩s, P.: User-model based personalized summarization. Information Processing & Management聽43(6), 1715鈥?734 (2007) CrossRef
  6. Frank, E., Paynter, G.W., Witten, I.H., Gutwin, C., Nevill Manning, C.G.: Domain-specific keyphrase extraction (1999)
  7. Hu, P., Ji, D.H., Teng, C., Guo, Y.: Context-enhanced personalized social summarization. In: COLING, pp. 1223鈥?238 (2012)
  8. Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL 2004 Workshop, pp. 74鈥?1 (2004)
  9. Lin, C.Y., Hovy, E.: The automated acquisition of topic signatures for text summarization. In: Proceedings of the 18th Conference on Computational Linguistics, vol.聽1, pp. 495鈥?01. Association for Computational Linguistics (2000)
  10. Luhn, H.P.: The automatic creation of literature abstracts. IBM Journal of Research and Development聽2(2), 159鈥?65 (1958) CrossRef
  11. Mihalcea, R., Tarau, P.: Textrank: Bringing order into texts. In: Proceedings of EMNLP, Barcelona, Spain, vol.聽4, p. 275 (2004)
  12. Paice, C.D., Jones, P.A.: The identification of important concepts in highly structured technical papers. In: Proceedings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 69鈥?8. ACM (1993)
  13. Qu, Y., Chen, Q.: Collaborative summarization: When collaborative filtering meets document summarization. In: PACLIC, pp. 474鈥?83 (2009)
  14. Sakai, H., Masuyama, S.: A multiple-document summarization system with user interaction. In: Proceedings of the 20th International Conference on Computational Linguistics, p. 1001. Association for Computational Linguistics (2004)
  15. Turney, P.D.: Learning algorithms for keyphrase extraction. Information Retrieval聽2(4), 303鈥?36 (2000) CrossRef
  16. Wan, X., Xiao, J.: Collabrank: towards a collaborative approach to single-document keyphrase extraction. In: Proceedings of the 22nd International Conference on Computational Linguistics, Association for Computational Linguistics, vol.聽1, pp. 969鈥?76 (2008)
  17. Wang, Y., Zhao, L., Zhang, Y.: Magiccube: choosing the best snippet for each aspect of an entity. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 1705鈥?708. ACM (2009)
  18. Yan, R., Nie, J.Y., Li, X.: Summarize what you are interested in: an optimization framework for interactive personalized summarization. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1342鈥?351. Association for Computational Linguistics (2011)
  
• 作者单位：Pingping Lin (22) (23)
  Shize Xu (22) (23)
  Yan Zhang (22) (23)
  
  22. Department of Machine Intelligence, Peking University, Beijing, 100871, China
  23. Key Laboratory on Machine Perception, Ministry of Education, Beijing, 100871, China
  
• ISSN：1611-3349

文摘

In this paper, we propose a framework to produce topic-focused summarization of news events, based on biased snippet extraction and selection. Through our approach, a summarization only retaining information related to a predefined topic (e.g. economy or politics) can be generated for a given news event to satisfy users with specific interests. To better balance coherence and coverage of the summarization, snippets rather than sentences or paragraphs are used as textual components. Topic signature is employed in snippet extraction and selection in order to emphasize the topic-biased information. Experiments conducted on real data demonstrate a good coverage, topic-relevancy, and content coherence of the summaries generated by our approach.