Extracting Contextual Information from Scientific Literature Using CERMINE System

Tkaczyk, Dominika; Bolikowski, Łukasz

doi:10.1007/978-3-319-25518-7_8

Cited by 7 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lopez (2009) launched the online tool GROBID (GeneRation Of BIbliographic Data) to identify and parse the citation anchors in citing documents. Tkaczyk and Bolikowski (2015) invented the tool CERMINE (Content ExtRactor and MINEr) to extract the context of citations. In a recent paper, Ahmad and Afzal (2018) proposed a CAD (Citation Anchor Detection) algorithm to identify citation anchors and their frequency in texts.…”

Section: Review Of In-text Citation Analysismentioning

confidence: 99%

A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Review Of In-text Citation Analysismentioning

confidence: 99%

A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies

et al. 2021

View full text Add to dashboard Cite

show abstract

“…DBLP computer science bibliography (DBLP) 20 is one of the exceptions, as it relies on an established and, thus reusable and reproducible, approach to generate its Linked Data set. The FacetedDBLP 21 is generated from data residing in DBLP databases by executing mapping rules described in D2RQ mapping language [5], the predecessor of the W3C recommended R2RML [6], and published using a D2R server 22 instance. Nevertheless, D2RQ may only be used with data residing or imported in a database, whereas our solution may also support data in other structures derived from different access interfaces.…”

Section: State Of the Artmentioning

confidence: 99%

“…The iLastic Enricher uses the Content ExtRactor and MINEr (cermine 40 ) [22] to extract the content of the corresponding pdf file. As soon as the publication's content is retrieved, its abstract and main body are fed to dbpedia spotlight 41 to identify and annotate entities that also appear in the dbpedia dataset.…”

Section: Linked Data Generationmentioning

confidence: 99%

ILastic: Linked Data Generation Workflow and User Interface for iMinds Scholarly Data

Dimou

Haesendonck

Vanbrabant

et al. 2018

Semantics, Analytics, Visualization

View full text Add to dashboard Cite

Enriching scholarly data with metadata enhances the publications' meaning. Unfortunately, different publishers of overlapping or complementary scholarly data neglect general-purpose solutions for metadata and instead use their own ad-hoc solutions. This leads to duplicate efforts and entails non-negligible implementation and maintenance costs. In this paper, we propose a reusable Linked Data publishing workflow that can be easily adjusted by different data owners to (i) generate and publish Linked Data, and (ii) align scholarly data repositories with enrichments over the publications' content. As a proof-of-concept, the proposed workflow was applied to the iMinds research institute data warehouse, which was aligned with publications' content derived from Ghent University's digital repository. Moreover, we developed a user interface to help lay users with the exploration of the iLastic Linked Data set. Our proposed approach relies on a general-purpose workflow. This way, we manage to reduce the development and maintenance costs and increase the quality of the resulting Linked Data.

show abstract

“…Tkaczyk & Bolikowski (2015) relied on CERMINE (http://cermine.ceon.pl/), an open source system for extracting structured metadata and references from scientific publications published as PDF files. It has a loosely captured architecture and a modular workflow based on supervised and unsupervised machine-learning techniques, which simplifies the systems adaptation to new document layouts and styles.…”

Section: Input: Training and Evaluation Datasetsmentioning

confidence: 99%

Challenges as enablers for high quality Linked Data: insights from the Semantic Publishing Challenge

Dimou

Vahdati

Iorio

et al. 2017

PeerJ Computer Science

View full text Add to dashboard Cite

While most challenges organized so far in the Semantic Web domain are focused on comparing tools with respect to different criteria such as their features and competencies, or exploiting semantically enriched data, the Semantic Web Evaluation Challenges series, co-located with the ESWC Semantic Web Conference, aims to compare them based on their output, namely the produced dataset. The Semantic Publishing Challenge is one of these challenges. Its goal is to involve participants in extracting data from heterogeneous sources on scholarly publications, and producing Linked Data that can be exploited by the community itself. This paper reviews lessons learned from both (i) the overall organization of the Semantic Publishing Challenge, regarding the definition of the tasks, building the input dataset and forming the evaluation, and (ii) the results produced by the participants, regarding the proposed approaches, the used tools, the preferred vocabularies and the results produced in the three editions of 2014, 2015 and 2016. We compared these lessons to other Semantic Web Evaluation Challenges. In this paper, we (i) distill best practices for organizing such challenges that could be applied to similar events, and (ii) report observations on Linked Data publishing derived from the submitted solutions. We conclude that higher quality may be achieved when Linked Data is produced as a result of a challenge, because the competition becomes an incentive, while solutions become better with respect to Linked Data publishing best practices when they are evaluated against the rules of the challenge.

show abstract

Extracting Contextual Information from Scientific Literature Using CERMINE System

Cited by 7 publications

References 5 publications

A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies

A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies

ILastic: Linked Data Generation Workflow and User Interface for iMinds Scholarly Data

Challenges as enablers for high quality Linked Data: insights from the Semantic Publishing Challenge

Contact Info

Product

Resources

About