CERMINE: automatic extraction of structured metadata from scientific literature

Tkaczyk, Dominika; Szostek, Pawel; Fedoryszak, Mateusz; Dendek, Piotr Jan; Bolikowski, Łukasz

doi:10.1007/s10032-015-0249-8

Cited by 150 publications

(144 citation statements)

References 26 publications

Supporting

Mentioning

136

Contrasting

Unclassified

Order By: Relevance

“…For this study, we processed documents in two formats: PDF (confirmed cases of AP) and LaTeX source code (NTCIR-11 MathIR Task dataset). We used GROBID to obtain bibliographic references from documents in both formats because the tool achieved excellent results for extracting header metadata, citations, and references [4,42]. Since GROBID cannot recognize mathematical formulae, we semi-automatically invoked InftyReader 6 to convert the PDFs for confirmed cases of AP to an intermediate LaTeX format.…”

Section: Preprocessingmentioning

confidence: 99%

Improving Academic Plagiarism Detection for STEM Documents by Analyzing Mathematical Content and Citations

Meuschke

Stange

Schubotz

et al. 2019

2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

Identifying academic plagiarism is a pressing task for educational and research institutions, publishers, and funding agencies. Current plagiarism detection systems reliably find instances of copied and moderately reworded text. However, reliably detecting concealed plagiarism, such as strong paraphrases, translations, and the reuse of nontextual content and ideas is an open research problem. In this paper, we extend our prior research on analyzing mathematical content and academic citations. Both are promising approaches for improving the detection of concealed academic plagiarism primarily in Science, Technology, Engineering and Mathematics (STEM). We make the following contributions: i) We present a two-stage detection process that combines similarity assessments of mathematical content, academic citations, and text. ii) We introduce new similarity measures that consider the order of mathematical features and outperform the measures in our prior research. iii) We compare the effectiveness of the math-based, citation-based, and text-based detection approaches using confirmed cases of academic plagiarism. iv) We demonstrate that the combined analysis of math-based and citation-based content features allows identifying potentially suspicious cases in a collection of 102K STEM documents. Overall, we show that analyzing the similarity of mathematical content and academic citations is a striking supplement for conventional textbased detection approaches for academic literature in the STEM disciplines. The data and code of our study are openly available at https://purl.org/hybridPD

show abstract

Section: Preprocessingmentioning

confidence: 99%

Improving Academic Plagiarism Detection for STEM Documents by Analyzing Mathematical Content and Citations

Meuschke

Stange

Schubotz

et al. 2019

2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

show abstract

“…In a recent survey and evaluation, several non-commercial reference parsing tools, Tkaczyk et al (2018) found that the best three performing ones all use a CRF approach: GROBID (Lopez, 2009), CERMINE (Tkaczyk et al, 2015) and ParsCit (Councill et al, 2008). All three benefit from task-specific tuning using extra annotated data, with GROBID showing the best off-the-shelf results.…”

Section: Related Workmentioning

confidence: 99%

Deep Reference Mining From Scholarly Literature in the Arts and Humanities

Alves

Colavizza

Kaplan

2018

Front. Res. Metr. Anal.

View full text Add to dashboard Cite

We consider the task of reference mining: the detection, extraction and classification of references within the full text of scholarly publications. Reference mining brings forward specific challenges, such as the need to capture the morphology of highly abbreviated words and the dependence among the elements of a reference, both following codified reference styles. This task is particularly difficult, and little explored, with respect to the literature in the arts and humanities, where references are mostly given in footnotes. We apply a deep learning architecture for reference mining from the full text of scholarly publications. We explore and discuss three architectural components: word and character-level word embeddings, different prediction layers (Softmax and Conditional Random Fields) and multi-task over single-task learning. Our best model uses both pre-trained word embeddings and characters embeddings, and a BiLSTM-CRF architecture. We test our solution on a dataset of annotated references from the historiography on Venice and, using a linear-chain CRF classifier as a baseline, we show that this deep learning architecture improves by a considerable margin. Furthermore, multi-task learning performs almost on par with a single-task approach. We thus confirm that there are important gains to be had by adopting deep learning for the task of reference mining.

show abstract

“…The large majority of full-texts collected by the system are PDF files, a for-mat well suited for printing and human reading, but less tractable by machines. For this reason, the full-text collection workflow includes a final phase designed to automatically extract structured metadata from such PDF files using CERMINE [2]. The extracted fulltexts are then stored in dedicated caches that are accessible by the OpenAIRE Information Inference System.…”

Section: Full-text Aggregationmentioning

confidence: 99%

The OpenAIRE Workflows for Data Management

Atzori

Bardi

Manghi

et al. 2017

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. The OpenAIRE initiative is the point of reference for Open Access in Europe and aims at the creation of an e-Infrastructure for the free flow, access, sharing, and re-use of research outcomes, services and processes for the advancement of research and the dissemination of scientific knowledge. OpenAIRE makes openly accessible a rich Information Space Graph (ISG) where products of the research life-cycle (e.g. publications, datasets, projects) are semantically linked to each other. Such an information space graph is constructed by a set of autonomic (orchestrated) workflows operating in a regimen of continuous data integration. This paper discusses the principal workflows operated by the Open-AIRE technical infrastructure in its different functional areas and provides the reader with the extent of the several challenges faced and the solutions realized. IntroductionThe OpenAIRE initiative is the point of reference for Open Access in Europe [3] [4]. Its mission is to foster an Open Science e-Infrastructure that links people, ideas and resources for the free flow, access, sharing, and re-use of research outcomes, services and processes for the advancement of research and the dissemination of scientific knowledge. OpenAIRE operates an open, collaborative, service oriented infrastructure that supports (i) the realization of a pan-European network for the definition, promotion and implementation of shared interoperability guidelines and best practices for managing, sharing, re-using, and preserving research outcomes of different typologies; (ii) the promotion of Open Science policies and practices at all stages of the research life-cycle and across research communities belonging to different application domains and geographical areas; (iii) the provision of measurements of the impact of Open Science and the return of investment of national and international funding agencies; (iv) the development and operation of a technical infrastructure supporting services for the discovery of and access to research outcomes via a centralized entry point, where research outcomes are enriched with contextual information via links to objects relevant to the research life-cycle. This paper focuses on the workflows operated by the OpenAIRE technical infrastructure for the management of the OpenAIRE information space. The

show abstract

CERMINE: automatic extraction of structured metadata from scientific literature

Cited by 150 publications

References 26 publications

Improving Academic Plagiarism Detection for STEM Documents by Analyzing Mathematical Content and Citations

Improving Academic Plagiarism Detection for STEM Documents by Analyzing Mathematical Content and Citations

Deep Reference Mining From Scholarly Literature in the Arts and Humanities

The OpenAIRE Workflows for Data Management

Contact Info

Product

Resources

About