Automatic classification of citation function

By Simone Teufel, Advaith Siddharthan, Dan Tidhar. Conference on Empirical Methods in Natural Language Processing, 2006

514 citations recorded by the source corpus.

Citation function is defined as the author's reason for citing a given paper (e.g. acknowledgement of the use of the cited method). The automatic recognition of the rhetorical function of citations in scientific text has many applications, from improvement of impact factor calculations to text summarisation and more informative citation indexers. We show that our annotation scheme for citation function is reliable, and present a supervised machine learning framework to automatically classify citation function, using both shallow and linguistically-inspired features. We find, amongst other things, a strong relationship between citation function and sentiment classification.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/9c93dd3ea94a3e81e6240a51968ad6f1d40380f3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Examining Citations of Natural Language Processing Literature (2020, methodology): “…AA have been used in the past for a number of tasks including: the study of citation patterns and intent (Pham and Hoffmann, 2003; Aya et al., 2005; Teufel et al., 2006; Mohammad et al., 2009; Nanba et al., 2011; Zhu et al., 2015; Radev et al., 2016), generating summaries of scientiﬁc articles…”
The State of NLP Literature: A Diachronic Analysis of the ACL Anthology (2019, background): “D L ] 8 N ov 2 01 9 Francopoulo, and Paroubek 2018; Qazvinian et al. 2013), on citation intent (Aya, Lagoze, and Joachims 2005; Teufel, Siddharthan, and Tidhar 2006; Pham and Hoffmann 2003; Nanba, Kando, and Okumura 2011; Mohammad et al. 2009; Zhu et al. 2015), and on measuring scholarly impact…”
Structural Scaffolds for Citation Intent Classification in Scientific Publications (2019, background): “There is a large body of work studying the intent of citations and devising categorization systems (Stevens and Giuliano, 1965; Moravcsik and Murugesan, 1975; Garzone and Mercer, 2000; White, 2004; Ahmed et al., 2004; Teufel et al., 2006; Agarwal et al., 2010; Dong and Schäfer, 2011).”
Argument Mining: A Survey (2020, background): “There are a broad range of manual schemes for classifying citation motivation and citation function (the reason why an author chooses to cite a paper), and Teufel, Siddharthan, and Tidhar (2006) look at how this classification can be automated.”
S2ORC: The Semantic Scholar Open Research Corpus (2020, background): “…sentiment (Athar and Teufel, 2012), identifying meaningful citations (Valenzuela et al., 2015), extracting key phrases (Caragea et al., 2014), and citation context-based paper summarization (Teufel et al., 2006; Qazvinian and Radev, 2008; Cohan and Goharian, 2015; Mitrović and Müller, 2015).”
The ACL Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics (2008, background): “The provision of a standardized collection of documents enables researchers to conduct research on topics of interest to the Digital Libraries and NLP communities.”
ParsCit: an Open-source CRF Reference String Parsing Package (2008, background): “Work continues in the community to utilize citation contexts to discern a citation’s function and compile a summary of how a work inﬂuences or is described by others (Teufel et al., 2006; Wu et al., 2006; Schwartz et al., 2007).”
Measuring the Evolution of a Scientific Field through Citation Frames (2018, methodology): “Therefore, we integrate portions of the dataset of Teufel (2010), 6 which has ﬁne-grained citation function labeled for ACL-related documents using the annotation scheme of Teufel et al. (2006b).”
Scientific Paper Summarization Using Citation Summary Networks (2008, background): “Although there has been work on analyzing citation and collaboration networks (Teufel et al., 2006; Newman, 2001) and scientiﬁc article summarization (Teufel and Moens, 2002), to the knowledge of the author there is no previous work that study the text of the citation summaries to produce a summary.”
GORC: A large contextual citation graph of academic papers (2019, background): “…(Cohan et al., 2019; Teufel et al., 2006), paper summarization (Cohan and Goharian, 2015; Mitrovic and M¨uller, 2015; Qazvinian and Radev, 2008; Teufel et al., 2006), citation analysis (Asa-tani et al., 2018; Jurgens et al., 2018, 2016; Ding et al., 2014), and more (Trujillo and Long, 2018;…”
Web of Science use in published research and review papers 1997–2017: a selective, dynamic, cross-domain, content-based analysis (2017, methodology): “NLP methods, especially part-of-speech (POS) tagging, sentiment analysis, and name-entity recognition, have been increasingly used by scientometricians to answer a wide range of research questions (Demarest and Sugimoto 2015; Pan et al. 2015; Small 2011; Teufel et al. 2006).”
The ACL anthology network corpus (2009, background): “2009), and citation function classification (Nanba et al. 2000; Teufel et al. 2006; Siddharthan and Teufel 2007; Teufel 2007).”
Citation recommendation: approaches and datasets (2020, unknown): “tation function can be determined – to some degree automatically – by analyzing the citation context and by extracting features [155,117,154].”
Coherent Citation-Based Summarization of Scientific Papers (2011, background): “Teufel et al. (2006) addressed the problem of classifying citations based on their function.”
Interpreting informational cues: An explorative study on information use among prospective homebuyers (2009, unknown): “Algorithmic citation analysis and natural language summarization have a long history (Teufel et al., 2006; Newman, 2001, Teufel and Moens, 2002).”