Scientific Paper Summarization Using Citation Summary Networks

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 689–696 Manchester, August 2008 Scientific Paper Summarization Using Citation Summary Networks Vahed Qazvinian School of Information University of Michigan Ann Arbor, MI vahed@umich.edu Dragomir R. Radev Department of EECS and School of Information University of Michigan Ann Arbor, MI radev@umich.edu Abstract Quickly moving to a new area of research is painful for researchers due to the vast amount of scientific literature in each field of study. One possible way to overcome this problem is to summarize a scientific topic. In this paper, we propose a model of summarizing a single article, which can be further used to summarize an entire topic. Our model is based on analyzing others’ viewpoint of the target article’s contribu- tions and the study of its citation summary network using a clustering approach. 1 Introduction It is quite common for researchers to have to quickly move into a new area of research. For instance, someone trained in text generation may want to learn about parsing and someone who knows summarization well, may need to learn about question answering. In our work, we try to make this transition as painless as possible by au- tomatically generating summaries of an entire re- search topic. This enables a researcher to find the chronological order and the progress in that par- ticular field of study. An ideal such system will re- ceive a topic of research, as the user query, and will return a summary of related work on that topic. In this paper, we take the first step toward building such a system. Studies have shown that different citations to the same article often focus on different aspects of that article, while none alone may cover a full descrip- tion of its entire contributions. Hence, the set of c⃝ 2008. Licensed under the Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported li- cense (http://creativecommons.org/licenses/by-nc-sa/3.0/). Some rights reserved. citation summaries, can be a good resource to un- derstand the main contributions of a paper and how that paper affects others. The citation summary of an article (A), as defined in (Elkiss et al., 2008), is a the set of citing sentences pointing to that ar- ticle. Thus, this source contains information about A from others’ point of view. Part of a sample ci- tation summary is as follows: In the context of DPs, this edge based factorization method was proposed by (Eisner, 1996). Eisner (1996) gave a generative model with a cubic parsing algorithm based on an edge factorization of trees. Eisner (Eisner, 1996) proposed an O(n3) parsing algorithm for PDG. If the parse has to be projective, Eisner’s bottom-up-span algorithm (Eisner, 1996) can be used for the search. The problem of summarizing a whole scientific topic, in its simpler form, may reduce to summa- rizing one particular article. A citation summary can be a good resource to make a summary of a target paper. Then using each paper’s summary and some knowledge of the citation network, we’ll be able …

Content truncated to 500 words