Difference between revisions of "Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents"
(Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents - basic info) |
(+ category) |
||
| (3 intermediate revisions by 3 users not shown) | |||
| Line 1: | Line 1: | ||
| − | '''Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents''' - scientific work related to Wikipedia quality published in 2018, written by Marcos Mouriño García, Roberto Pérez Rodríguez and Luis Anido Rifón. | + | {{Infobox work |
| + | | title = Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents | ||
| + | | date = 2018 | ||
| + | | authors = [[Marcos Mouriño García]]<br />[[Roberto Pérez Rodríguez]]<br />[[Luis Anido Rifón]] | ||
| + | | doi = 10.1016/j.artmed.2018.04.007 | ||
| + | | link = https://www.sciencedirect.com/science/article/pii/S0933365717304153 | ||
| + | }} | ||
| + | '''Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents''' - scientific work related to [[Wikipedia quality]] published in 2018, written by [[Marcos Mouriño García]], [[Roberto Pérez Rodríguez]] and [[Luis Anido Rifón]]. | ||
== Overview == | == Overview == | ||
| − | Abstract This article presents a classifier that leverages Wikipedia knowledge to represent documents as vectors of concepts weights, and analyses its suitability for classifying biomedical documents written in any language when it is trained only with English documents. Authors propose the cross-language concept matching technique, which relies on Wikipedia interlanguage links to convert concept vectors between languages. The performance of the classifier is compared to a classifier based on machine translation, and two classifiers based on MetaMap. To perform the experiments, authors created two multilingual corpus. The first one, Multi-Lingual UVigoMED (ML-UVigoMED) is composed of 23,647 Wikipedia documents about biomedical topics written in English, German, French, Spanish, Italian, Galician, Romanian, and Icelandic. The second one, English-French-Spanish-German UVigoMED (EFSG-UVigoMED) is composed of 19,210 biomedical abstract extracted from MEDLINE written in English, French, Spanish, and German. The performance of the approach proposed is superior to any of the state-of-the art classifier in the benchmark. Authors conclude that leveraging Wikipedia knowledge is of great advantage in tasks of multilingual classification of biomedical documents. | + | Abstract This article presents a classifier that leverages [[Wikipedia]] knowledge to represent documents as vectors of concepts weights, and analyses its suitability for classifying biomedical documents written in any language when it is trained only with English documents. Authors propose the cross-language concept matching technique, which relies on Wikipedia interlanguage links to convert concept vectors between languages. The performance of the classifier is compared to a classifier based on [[machine translation]], and two classifiers based on MetaMap. To perform the experiments, authors created two [[multilingual]] corpus. The first one, Multi-Lingual UVigoMED (ML-UVigoMED) is composed of 23,647 Wikipedia documents about biomedical topics written in English, German, French, Spanish, Italian, Galician, Romanian, and Icelandic. The second one, English-French-Spanish-German UVigoMED (EFSG-UVigoMED) is composed of 19,210 biomedical abstract extracted from MEDLINE written in English, French, Spanish, and German. The performance of the approach proposed is superior to any of the state-of-the art classifier in the benchmark. Authors conclude that leveraging Wikipedia knowledge is of great advantage in tasks of multilingual classification of biomedical documents. |
| + | |||
| + | == Embed == | ||
| + | === Wikipedia Quality === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | García, Marcos Mouriño; Rodríguez, Roberto Pérez; Rifón, Luis Anido. (2018). "[[Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents]]". Elsevier. DOI: 10.1016/j.artmed.2018.04.007. | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === English Wikipedia === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | {{cite journal |last1=García |first1=Marcos Mouriño |last2=Rodríguez |first2=Roberto Pérez |last3=Rifón |first3=Luis Anido |title=Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents |date=2018 |doi=10.1016/j.artmed.2018.04.007 |url=https://wikipediaquality.com/wiki/Leveraging_Wikipedia_Knowledge_to_Classify_Multilingual_Biomedical_Documents |journal=Elsevier}} | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === HTML === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | García, Marcos Mouriño; Rodríguez, Roberto Pérez; Rifón, Luis Anido. (2018). &quot;<a href="https://wikipediaquality.com/wiki/Leveraging_Wikipedia_Knowledge_to_Classify_Multilingual_Biomedical_Documents">Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents</a>&quot;. Elsevier. DOI: 10.1016/j.artmed.2018.04.007. | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | |||
| + | |||
| + | [[Category:Scientific works]] | ||
| + | [[Category:English Wikipedia]] | ||
| + | [[Category:German Wikipedia]] | ||
| + | [[Category:French Wikipedia]] | ||
| + | [[Category:Italian Wikipedia]] | ||
| + | [[Category:Spanish Wikipedia]] | ||
| + | [[Category:Romanian Wikipedia]] | ||
| + | [[Category:Galician Wikipedia]] | ||
| + | [[Category:Icelandic Wikipedia]] | ||
| + | [[Category:Romani Wikipedia]] | ||
Latest revision as of 08:49, 23 December 2020
Authors | Marcos Mouriño García Roberto Pérez Rodríguez Luis Anido Rifón |
|---|---|
Publication date | 2018 |
DOI | 10.1016/j.artmed.2018.04.007 |
Links | Original |
Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents - scientific work related to Wikipedia quality published in 2018, written by Marcos Mouriño García, Roberto Pérez Rodríguez and Luis Anido Rifón.
Overview
Abstract This article presents a classifier that leverages Wikipedia knowledge to represent documents as vectors of concepts weights, and analyses its suitability for classifying biomedical documents written in any language when it is trained only with English documents. Authors propose the cross-language concept matching technique, which relies on Wikipedia interlanguage links to convert concept vectors between languages. The performance of the classifier is compared to a classifier based on machine translation, and two classifiers based on MetaMap. To perform the experiments, authors created two multilingual corpus. The first one, Multi-Lingual UVigoMED (ML-UVigoMED) is composed of 23,647 Wikipedia documents about biomedical topics written in English, German, French, Spanish, Italian, Galician, Romanian, and Icelandic. The second one, English-French-Spanish-German UVigoMED (EFSG-UVigoMED) is composed of 19,210 biomedical abstract extracted from MEDLINE written in English, French, Spanish, and German. The performance of the approach proposed is superior to any of the state-of-the art classifier in the benchmark. Authors conclude that leveraging Wikipedia knowledge is of great advantage in tasks of multilingual classification of biomedical documents.
Embed
Wikipedia Quality
García, Marcos Mouriño; Rodríguez, Roberto Pérez; Rifón, Luis Anido. (2018). "[[Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents]]". Elsevier. DOI: 10.1016/j.artmed.2018.04.007.
English Wikipedia
{{cite journal |last1=García |first1=Marcos Mouriño |last2=Rodríguez |first2=Roberto Pérez |last3=Rifón |first3=Luis Anido |title=Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents |date=2018 |doi=10.1016/j.artmed.2018.04.007 |url=https://wikipediaquality.com/wiki/Leveraging_Wikipedia_Knowledge_to_Classify_Multilingual_Biomedical_Documents |journal=Elsevier}}
HTML
García, Marcos Mouriño; Rodríguez, Roberto Pérez; Rifón, Luis Anido. (2018). "<a href="https://wikipediaquality.com/wiki/Leveraging_Wikipedia_Knowledge_to_Classify_Multilingual_Biomedical_Documents">Leveraging Wikipedia Knowledge to Classify Multilingual Biomedical Documents</a>". Elsevier. DOI: 10.1016/j.artmed.2018.04.007.
