Towards Open Corpus Adaptive E-learning Systems on the Web

Kravčík, Miloš; Wan, Jian

doi:10.1007/978-3-642-41175-5_12

Cited by 4 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…System functionality was enhanced by linking closed corpus resources with open corpus content (Brusilovsky & Rizzo, 2002;Brusilovsky, Chavan, & Farzan, 2004;Dolog, Henze, Nejdl, & Sintek, 2004;Henze & Nejdl, 2001). Systems purely using OCR gained traction with the efforts of (Kravčík & Wan, 2013;Lawless & Wade, 2006;Lawless et al, 2008;Levacher, Hynes, Lawless, O'Connor, & Wade, 2009;Lin & Brusilovsky, 2011;Muntean & Muntean, 2009;Sosnovsky et al, 2012;Steichen, Lawless, O'Connor, & Wade, 2009) and is still an ongoing area of active research with huge potential and challenges.…”

Section: Discussion On Open Corpus Systemsmentioning

confidence: 99%

“…The authors claim that during evaluation the system demonstrated learning outcomes comparable to CCSs. Kravčík and Wan (2013) use domain ontology for document mapping. By considering domain ontology as a network of concepts represented in a formal and explicit manner, the author's exploit formalization afforded by ontology for standardized representation, mapping, querying, and reasoning.…”

Section: Systems Exclusively Using Open Corpus Resourcesmentioning

confidence: 99%

“…Lack or insufficient metadata, varying metadata standards; problems of natural language in the description of learning resources pose barriers to automatic analysis of content. Some automated tools like Semtag, Metasaur (Kravčík & Wan, 2013) exist for automatic metadata annotation but are of little use to deal with diverse knowledge domains. As a consequence, there is no interoperability between systems and difficulty is experienced in deriving semantic knowledge by machine processing of content (Lawless & Wade, 2006).…”

Section: Metadata and Indexingmentioning

confidence: 99%

“…The systems discussed (Kravčík & Wan, 2013;Steichen et al, 2009;Sosnovsky et al, 2012) have a process which is customized to specific problem types or domains. Enlarging the scope to handle diverse knowledge domains is needed.…”

Section: Access Barriers and Domain Neutral Solutionsmentioning

confidence: 99%

See 3 more Smart Citations

The open corpus challenge in eLearning

Pattanshetti

Jasola²,

Gupta³

et al. 2018

Knowledge Management &Amp; E-Learning: An International Journal

View full text Add to dashboard Cite

Learning has transcended into a life-long endeavor in the information age. It is no longer restricted to confines of formal classrooms. Consequently, a student is not restricted to traditional learning resources like teachers, textbooks or printed content. Digital resources available on the Internet form a very significant component of self-learning. Copious volumes of learning resources without legal barriers to self-learning reside in digital repositories, educational institution portals and on numerous websites. Learners wishing to utilize the web for personalized learning are faced with a daunting array of content to wade through and select the suitable ones to fulfill his/her learning objectives. Therefore, it is not a question of availability; it is one of relevance and suitability. Typically, in addition to time constraints, learners lack the expertise to screen content for effective eLearning. Adaptive hypermedia systems (AHSs) offer a path to harnessing this large volume of learning resources for personalized learning. This review paper provides a concise and coherent discussion about the evolution of AHSs along with the challenges that need to be addressed for effectively harnessing openly available educational resources referred to as open corpus resources (OCRs).

show abstract

Section: Discussion On Open Corpus Systemsmentioning

confidence: 99%

Section: Systems Exclusively Using Open Corpus Resourcesmentioning

confidence: 99%

Section: Metadata and Indexingmentioning

confidence: 99%

Section: Access Barriers and Domain Neutral Solutionsmentioning

confidence: 99%

See 2 more Smart Citations

The open corpus challenge in eLearning

Pattanshetti

Jasola²,

Gupta³

et al. 2018

Knowledge Management &Amp; E-Learning: An International Journal

View full text Add to dashboard Cite

show abstract

“…Machine learning methods are widely used in data mining and document analysis tasks [5][6][7][8][9][10]. Automatic classification systems have been applied to mail classification, electronic conference, information filtering, and so on [11][12][13][14][15]. The Xgboost algorithm [16] implements the GBDT algorithm and has been widely used in competitions and many other machine learning projects and achieved satisfying results [17,18].…”

Section: Related Studies and The Current Contributionmentioning

confidence: 99%

DWSA: An Intelligent Document Structural Analysis Model for Information Extraction and Data Mining

Yue

2021

Electronics

View full text Add to dashboard Cite

The structure of a document contains rich information such as logical relations in context, hierarchy, affiliation, dependence, and applicability. It will greatly affect the accuracy of document information processing, particularly of legal documents and business contracts. Therefore, intelligent document structural analysis is important to information extraction and data mining. However, unlike the well-studied field of text semantic analysis, current work in document structural analysis is still scarce. In this paper, we propose an intelligent document structural analysis framework through data pre-processing, feature engineering, and structural classification with a dynamic sample weighting algorithm. As a typical application, we collect more than 11,000 insurance document content samples and carry out the machine learning experiments to check the efficiency of our framework. Meanwhile, to address the sample imbalance problem in the hierarchy classification task, a dynamic sample weighting algorithm is incorporated into our Dynamic Weighting Structural Analysis (DWSA) framework, in which the weights of different category tags according to the structural levels are iterated dynamically in training. Our results show that the DWSA has significantly improved the comprehensive accuracy and the classification F1-score of each category. The comprehensive accuracy is as high as 94.68% (3.36% absolute improvement) and the Macro F1-score is 88.29% (5.1% absolute improvement).

show abstract

Computer Science Paper Classification for CSAR

Quan

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards Open Corpus Adaptive E-learning Systems on the Web

Cited by 4 publications

References 11 publications

The open corpus challenge in eLearning

The open corpus challenge in eLearning

DWSA: An Intelligent Document Structural Analysis Model for Information Extraction and Data Mining

Computer Science Paper Classification for CSAR

Contact Info

Product

Resources

About