A modular information extraction system

Feldman, Ronen; Regev, Yizhar; Gorodetsky, Maya

doi:10.3233/ida-2008-12104

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information extraction is a component of natural language processing (NLP) that focuses on finding the relationships between particular entities of scientific articles . These entities include authors, affiliations, citations, keywords, and so forth.…”

Section: Methodsmentioning

confidence: 99%

The Quantitative Evaluation of the Clinical and Translational Science Awards (CTSA) Program Based on Science Mapping and Scientometric Analysis

Zhang¹,

Wang²,

Tian-xi³

2013

Clinical Translational Sci

View full text Add to dashboard Cite

The Clinical and Translational Science Awards (CTSA) program is one of the most important initiatives in translational medical funding. The quantitative evaluation of the efficiency and performance of the CTSA program has a significant referential meaning for the decision making of global translational medical funding. Using science mapping and scientometric analytic tools, this study quantitatively analyzed the scientific articles funded by the CTSA program. The results of the study showed that the quantitative productivities of the CTSA program had a stable increase since 2008. In addition, the emerging trends of the research funded by the CTSA program covered clinical and basic medical research fields. The academic benefits from the CTSA program were assisting its members to build a robust academic home for the Clinical and Translational Science and to attract other financial support. This study provided a quantitative evaluation of the CTSA program based on science mapping and scientometric analysis. Further research is required to compare and optimize other quantitative methods and to integrate various research results. Clin Trans Sci 2013; Volume 6: 452-457

show abstract

Section: Methodsmentioning

confidence: 99%

The Quantitative Evaluation of the Clinical and Translational Science Awards (CTSA) Program Based on Science Mapping and Scientometric Analysis

Zhang¹,

Wang²,

Tian-xi³

2013

Clinical Translational Sci

View full text Add to dashboard Cite

show abstract

“…In contrast, the community of natural language processing (NLP) has not managed to standardize a core language for writing information extractors. Rather, this community relies on academic initiatives, such as GATE [18], commercial languages like AQL [14] or DIAL [28], integration frameworks like UIMA [29], RUTA [36] or in-house extractors based on regular expressions, R, Python or Java. Ordinary SQL developers will often not be willing to learn and understand the differences and flavors of these abstraction principles.…”

Section: Problem Statementmentioning

confidence: 99%

INDREX: In-database relation extraction

Kilias

Löser

Andritsos

2015

Information Systems

View full text Add to dashboard Cite

“…2,15,22,27,30,39 On the other hand, Artificial Intelligence techniques, in particular Knowledge Engineering and Machine Learning (ML), have been largely used in IE from structured and semistructured text.…”

Section: Information Extraction Techniquesmentioning

confidence: 99%

Combining Text Classifiers and Hidden Markov Models for Information Extraction

Barros

Silva

Prudêncio

et al. 2009

Int. J. Artif. Intell. Tools

View full text Add to dashboard Cite

In this paper, we propose a hybrid machine learning approach to Information Extraction by combining conventional text classification techniques and Hidden Markov Models (HMM). A text classifier generates a (locally optimal) initial output, which is refined by an HMM, providing a globally optimal classification. The proposed approach was evaluated in two case studies and the experiments revealed a consistent gain in performance through the use of the HMM. In the first case study, the implemented prototype was used to extract information from bibliographic references, reaching a precision rate of 87.48% in a test set with 3000 references. In the second case study, the prototype extracted information from author affiliations, reaching a precision rate of 90.27% in a test set with 300 affiliations.

show abstract

A modular information extraction system

Cited by 9 publications

References 17 publications

The Quantitative Evaluation of the Clinical and Translational Science Awards (CTSA) Program Based on Science Mapping and Scientometric Analysis

The Quantitative Evaluation of the Clinical and Translational Science Awards (CTSA) Program Based on Science Mapping and Scientometric Analysis

INDREX: In-database relation extraction

Combining Text Classifiers and Hidden Markov Models for Information Extraction

Contact Info

Product

Resources

About