Characterizing human summarization strategies for text reuse and transformation in literature review writing
Citations are useful signals of information salience, but little research has identified the patterns of information selection, transformation, and organization that they espouse. This paper investigated the summarization strategies followed in the writing of literature review sections of information science research papers. We found that the summarization strategies followed are different for the two major styles of literature review writing, descriptive versus integrative literature reviews. Descriptive literature reviews, which focus on individual descriptions of research papers, are more likely to reference the Method and the Result sections of the cited paper and copy-paste text the referenced text. In contrast, integrative literature reviews, which synthesize the main ideas for many papers together, have more critiques and focus mainly on the Conclusion sections. These findings, based on a hand-annotated dataset, have the potential to scale up into a transformation-invariant neural architecture for scientific summarization that can generate different summaries of the input text with integrative or descriptive characteristics.
KeywordsLiterature review writing Scientific summarization Discourse analysis Citance Abstracting Citation analysis
Mathematics Subject Classification62H20
- Abura’ed, A., Bravo, A., Chiruzzo, L., & Saggion, H. (2018). LaSTUS/TALN + INCO@ CL-SciSumm 2018-using regression and convolutions for cross-document semantic linking and summarization of scholarly literature. In Proceedings of the 3nd joint workshop on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL2018). Ann Arbor, Michigan (July 2018).Google Scholar
- Bourner, T. (1996). The research process: Four steps to success. Research methods: guidance for postgraduates, Arnold, London, pp. 7–11.Google Scholar
- Buchanan, G., & McKay, D. (2017). The lowest form of flattery: characterising text re-use and plagiarism patterns in a digital library corpus. In Proceedings of the ACM/IEEE joint conference on digital libraries (pp. 1–10). IEEE.Google Scholar
- Dijk, T. A. (1979). Macrostructures: An interdisciplinary study of global structures in discourse, interaction, and cognition. New York: L. Erlbaum Associates.Google Scholar
- Guo, Q., & Li, C. (2007). The research on the application of text clustering and natural language understanding in automatic abstracting. In Fourth international conference on fuzzy systems and knowledge discovery, 2007. FSKD 2007. (vol. 4, pp. 92–96). IEEE.Google Scholar
- Hart, C. (1998). Doing a literature review. London: Sage.Google Scholar
- Jaidka, K., Khoo, C., & Na, J. C. (2010). Imitating human literature review writing: an approach to multi-document summarization. In Proceedings of the international conference on asian digital libraries (pp. 116–119). Springer, Berlin, Heidelberg.Google Scholar
- Jaidka, K., Khoo, C., & Na, J. C. (2013a). Deconstructing human literature reviews–a framework for multi-document summarization. In proceedings of the 14th European workshop on natural language generation (pp. 125–135).Google Scholar
- Jing, H., & McKeown, K. R. (1999). The decomposition of human-written summary sentences. In Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval (pp. 129–136). ACM.Google Scholar
- Kan, M. Y., Klavans, J. L., & McKeown, K. R. (2002). Using the annotated bibliography as a resource for indicative summarization. In Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02).Google Scholar
- Knott, D. (1999). Writing an annotated bibliography. Retrieved January 2009. http://www.writing.utoronto.ca/advice/specific-types-of-writing/annotated-bibliography.
- Liu, Y., Wang, X., Zhang, J., & Xu, H. (2008). Personalized PageRank based multi-document summarization. In IEEE international workshop on semantic computing and systems, 2008. WSCS’08. (pp. 169–173). IEEE.Google Scholar
- Massey, A. (1996). Using the literature: 3 × 4 analogies. The Qualitative Report, 2(4). Retrieved from January 2009. http://www.nova.edu/ssss/QR/QR2-4/massey.html.
- Mei, Q., & Zhai, C. (2008). Generating impact-based summaries for scientific literature. In Proceedings of the ACL conference on human language technologies (pp. 816–824). Association for Computational Linguistics.Google Scholar
- Mohammad, S., Dorr, B., Egan, M., Hassan, A., Muthukrishan, P., Qazvinian, V., & Zajic, D. (2009). Using citations to generate surveys of scientific paradigms. In Proceedings of human language technologies: The 2009 annual conference of the north american chapter of the association for computational linguistics (pp. 584–592). Association for Computational Linguistics.Google Scholar
- Nanba, H. (2000). Classification of research papers using citation links and citation types: Towards automatic review article generation. In Proceedings of the American Society for Information Science (ASIS)/the 11th SIG classification research workshop, classification for user support and learning, Chicago, USA, 2000 (pp. 117–134). Morgan Kaufmann Publishers.Google Scholar
- Nanba, H., & Okumura, M. (1999). Towards multi-paper summarization reference information. In Proceedings of the 16th international joint conference on Artificial intelligence-Volume 2 (pp. 926–931). Morgan Kaufmann Publishers Inc.Google Scholar
- Nanba, H., & Okumura, M. (2005). Automatic detection of survey articles. In International Conference on Theory and Practice of Digital Libraries (pp. 391–401). Springer, Berlin, Heidelberg.Google Scholar
- Nomoto, T. (2016). NEAL: A neurally enhanced approach to linking citation and reference. In Proceedings of the joint workshop on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL) (pp. 168–174).Google Scholar
- Qazvinian, V., & Radev, D. R. (2010). Identifying non-explicit citing sentences for citation-based summarization. In Proceedings of the 48th annual meeting of the association for computational linguistics (pp. 555–564). Association for Computational Linguistics.Google Scholar
- Qazvinian, V., Radev, D. R., & Özgür, A. (2010). Citation summarization through keyphrase extraction. In Proceedings of the 23rd international conference on computational linguistics (pp. 895–903). Association for Computational Linguistics.Google Scholar
- Rush, A. M., Chopra, S., & Weston, J. (2015). A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 conference on empirical methods in natural language processing (pp. 379–389).Google Scholar
- Singh, M., Niranjan, A., Gupta, D., Bakshi, N. A., Mukherjee, A., & Goyal, P. (2017). Citation sentence reuse behavior of scientists: A case study on massive bibliographic text dataset of computer science. In Proceedings of the ACM/IEEE joint conference on digital libraries (JCDL) (pp. 1–4). IEEE.Google Scholar
- Tandon, N., & Jain, A. (2012). Citation context sentiment analysis for structured summarization of research papers. In 35th German conference on artificial intelligence (p. 98).Google Scholar
- Teufel, S. (1999). Argumentative Zoning: Information Extraction from scientific text. Ph.D. Thesis, University of Edinburgh.Google Scholar
- Teufel, S., Carletta, J., & Moens, M. (1999). An annotation scheme for discourse-level argumentation in research articles. In Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics (pp. 110–117). Association for Computational Linguistics.Google Scholar
- Yasunaga, M., Kasai, J., Zhang, R., Dan, A. R. F. I. L., & Radev, F. D. R. (2019). ScisummNet: A large annotated corpus and content-impact models for scientific paper summarization with citation networks. In Proceedings of the AAAI annual meeting.Google Scholar
- Zhang, Y., Barzilay, R., & Jaakkola, T. (2017). Aspect-augmented adversarial networks for domain adaptation. arXiv preprint arXiv:1701.00188.
- Zhao, J. J., Kim, Y., Zhang, K., Rush, A. M., & LeCun, Y. (2017). Adversarially regularized autoencoders for generating discrete structures. CoRR, abs/1706.04223.Google Scholar