Towards an Automated Citation Classifier

Garzone, Mark; Mercer, Robert E.

doi:10.1007/3-540-45486-1_28

Cited by 68 publications

(56 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison with Garzone and Mercer [28-30] or Radoulov's citation schema [31], our citation schema is more simplified and intuitive, and therefore easier to annotate. Even so, we found that annotating certain relations (e.g., cause and quantitative evaluation ) suffered from a low number of occurrences and poor agreement, even after successive iterations.…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…To identify and define specific citation relations, we studied the citation categories proposed in previous studies [6,12-24,28-31] before examining and annotating seven randomly selected full-text biomedical articles. We then refine this top-down citation schema through a bottom-up approach.…”

Section: Methodsmentioning

confidence: 99%

“…Garzone and Mercer [28-30] treated the citation classification as a task of sentence categorization. They extracted a sentence that incorporated citations and then applied manually curated lexical and grammar rules to assign the citations to one of 35 predefined categories.…”

Section: Introductionmentioning

confidence: 99%

“…They extracted a sentence that incorporated citations and then applied manually curated lexical and grammar rules to assign the citations to one of 35 predefined categories. These categories included “citing work totally disputes some aspect of cited work,” “citing work totally confirms cited work,” and “citing work refers to assumed knowledge which is general background.” More recently, Radoulov [31] built upon the work of Garzone and Mercer [28-30] to develop supervised machine-learning approaches for automatic citation classification. The citation schema they built including reason for citation and what is cited.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Investigating and annotating the role of citation in biomedical full-text articles

Agarwal

Frid

2009

2009 IEEE International Conference on Bioinformatics and Biomedicine Workshop

View full text Add to dashboard Cite

Citations are ubiquitous in scientific articles and play important roles for representing the semantic content of a full-text biomedical article. In this work, we manually examined full-text biomedical articles to analyze the semantic content of citations in full-text biomedical articles. After developing a citation relation schema and annotation guideline, our pilot annotation results show an overall agreement of 0.71, and here we report on the research challenges and the lessons we've learned while trying to overcome them. Our work is a first step toward automatic citation classification in full-text biomedical articles, which may contribute to many text mining tasks, including information retrieval, extraction, summarization, and question answering.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigating and annotating the role of citation in biomedical full-text articles

Agarwal

Frid

2009

2009 IEEE International Conference on Bioinformatics and Biomedicine Workshop

View full text Add to dashboard Cite

show abstract

“…To address this problem, the aim of formal citation analysis has been to categorize and, ultimately, automatically classify scientific citations. In previous work, Garzone and Mercer (2000) presented a system for citation classification that relied on characteristic syntactic structure to determine citation category. In this present work, we extend this idea to propose that fine-grained cue phrases within citation sentences may provide a stylistic basis for just such a categorization.…”

Section: Learning By Discovering Conflictsmentioning

confidence: 99%

Advances in Artificial Intelligence

Xiang¹,

Chaib-draa²

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

PrefaceThe AI 2003 conference was the 16th in the series of artificial intelligence conferences sponsored by the Canadian Society for Computational Studies of Intelligence (CSCSI)/Société Canadienne pour l'Étude de l'Intelligence par Ordinateur (SCEIO). The conference showcases the excellent research work done by Canadians and their international colleagues. As in the case of many past Canadian AI conferences, AI 2003 was organized in conjunction with its sister Canadian conferences, Vision Interface (VI) and Graphics Interface (GI), enriching the experience for all participants. The conferences were held on the campus of Dalhousie University, at Canada's largest Atlantic port city, Halifax.This year, we received a record number of paper submissions. A total of 116 abstracts were received, out of which 106 papers were submitted by the due date. As at past conferences, there was strong international participation. Among the submitted papers, about 41% were from non-Canadian researchers. From the 106 papers, we accepted 30 full papers and 24 short papers. Following the success in AI 2002, the Graduate Student Symposium was continued in AI 2003, with 11 extended abstracts accepted from 16 submissions. All these accepted papers are included in this volume. They cover a wide range of topics, including knowledge representation, search, constraint satisfaction, natural language, machine learning and data mining, reasoning under uncertainty, agent and multiagent systems, AI and Web applications, AI and bioinformatics, and AI and E-commerce.We invited three distinguished researchers representing three very active subfields of AI: Victor Lesser (multiagent systems), Tom Mitchell (machine learning), and Pierre Baldi (AI and bioinformatics). The extended abstracts of their invited talks also appear in this volume.Many contributed to the organization of AI 2003. Members of the Program Committee made helpful suggestions on the conference organization. They and the associated referees carefully and critically reviewed all submissions and ensured a high-quality technical program. The National Research Council of Canada and the Canadian Society for Computational Studies of Intelligence provided travel support for the Graduate Student Symposium. CSCSI's past president Bob Mercer and president Bruce Spencer gave us much guidance whenever needed. The conference chair Charles Ling and the local organizer Malcolm Heywood attended to many organizational details. We thank the invited speakers, all authors who submitted their work to AI 2003, and the conference participants. We thank the AI-GI-VI Steering Committee and the organizers of GI and VI for their cooperation. Our home institutions, the University of Guelph and Laval University, and the host institution of the conference, Dalhousie University, provided much assistance and support. Alfred Hofmann and Ursula Barth at Springer-Verlag assisted the publication of this volume. Graduate students Feng Zou, Junjiang Chen, Xiaoyun Chen and Xiangdong An assisted in devel-VI Preface oping a...

show abstract

Measuring academic influence: Not all citations are equal

Zhu

Turney

Lemire

et al. 2014

Asso for Info Science & Tech

196

197

View full text Add to dashboard Cite

The importance of a research article is routinely measured by counting how many times it has been cited. However, treating all citations with equal weight ignores the wide variety of functions that citations perform. We want to automatically identify the subset of references in a bibliography that have a central academic influence on the citing paper. For this purpose, we examine the effectiveness of a variety of features for determining the academic influence of a citation.By asking authors to identify the key references in their own work, we created a dataset in which citations were labeled according to their academic influence. Using automatic feature selection with supervised machine learning, we found a model for predicting academic influence that achieves good performance on this dataset using only four features.The best features, among those we evaluated, were features based on the number of times a reference is mentioned in the body of a citing paper. The performance of these features inspired us to design an influence-primed h-index (the hip-index). Unlike the conventional h-index, it weights citations by how many times a reference is mentioned. According to our experiments, the hip-index is a better indicator of researcher performance than the conventional h-index.

show abstract

Towards an Automated Citation Classifier

Cited by 68 publications

References 6 publications

Investigating and annotating the role of citation in biomedical full-text articles

Investigating and annotating the role of citation in biomedical full-text articles

Advances in Artificial Intelligence

Measuring academic influence: Not all citations are equal

Contact Info

Product

Resources

About