Rediscovering ACL Discoveries Through the Lens of ACL Anthology Network Citing Sentences

Proceedings of the ACL-2012 Special Workshop on Rediscovering 50 Years of Discoveries, pages 1–12, Jeju, Republic of Korea, 10 July 2012. c⃝2012 Association for Computational Linguistics Rediscovering ACL Discoveries Through the Lens of ACL Anthology Network Citing Sentences Dragomir Radev EECS Department University of Michigan Ann Arbor, MI, USA radev@umich.edu Amjad Abu-Jbara EECS Department University of Michigan Ann Arbor, MI, USA amjbara@umich.edu Abstract The ACL Anthology Network (AAN)1 is a comprehensive manually curated networked database of citations and collaborations in the field of Computational Linguistics. Each cita- tion edge in AAN is associated with one or more citing sentences. A citing sentence is one that appears in a scientific article and con- tains an explicit reference to another article. In this paper, we shed the light on the usefulness of AAN citing sentences for understanding re- search trends and summarizing previous dis- coveries and contributions. We also propose and motivate several different uses and appli- cations of citing sentences. 1 Introduction The ACL Anthology2 is one of the most success- ful initiatives of the Association for Computational Linguistics (ACL). It was initiated by Steven Bird in 2001 and is now maintained by Min-Yen Kan. It includes all papers published by ACL and related or- ganizations as well as the Computational Linguistics journal over a period of four decades. The ACL Anthology Network (AAN) is another successful initiative built on top of the ACL Anthol- ogy. It was started in 2007 by our group (Radev et al., 2009) at the University of Michigan. AAN provides citation and collaboration networks of the articles included in the ACL Anthology (excluding book reviews). AAN also includes rankings of pa- pers and authors based on their centrality statistics 1http://clair.si.umich.edu/anthology/ 2http://www.aclweb.org/anthology-new/ in the citation and collaboration networks. It also includes the citing sentences associated with each citation link. These sentences were extracted auto- matically using pattern matching and then cleaned manually. Table 1 shows some statistics of the cur- rent release of AAN. The text surrounding citations in scientific publi- cations has been studied and used in previous work. Nanba and Okumura (1999) used the term citing area to refer to citing sentences. They define the cit- ing area as the succession of sentences that appear around the location of a given reference in a scien- tific paper and has connection to it. They proposed a rule-based algorithm to identify the citing area of a given reference. In (Nanba et al., 2000) they use their citing area identification algorithm to identify the purpose of citation (i.e. the author’s reason for citing a given paper.) Nakov et al. (2004) use the term citances to refer to citing sentences. They explored several different uses of citances including the creation of training and testing data for semantic analysis, synonym set creation, database curation, summarization, and in- formation retrieval. Other previous studies have used citing sentences in various applications such as: scientific paper summarization (Elkiss et al., 2008; Qazvinian and Radev, 2008; Mei and Zhai, 2008; Qazvinian et al., 2010; …

Content truncated to 500 words