Disentangling the Wikipedia Category Graph for Corpus Extraction
Fuente:
Redalyc
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artículo científico |
| Lingua: | en |
| Pubblicazione: |
Instituto Politécnico Nacional
2009
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1876470467277094912 |
|---|---|
| author | Axel-Cyrille Ngonga Ngomo |
| author_facet | Axel-Cyrille Ngonga Ngomo |
| contents | Disentangling the Wikipedia Category Graph for Corpus Extraction Axel-Cyrille Ngonga Ngomo Frank Schumacher Computación corpus extraction local graph clustering Natural language processing In several areas of research such as knowledgemanagement and natural language processing, domain-specificcorpora are required for tasks such as terminology extraction andontology learning. The presented investigations herein are basedon the assumption that Wikipedia can be used for the purposeof corpus extraction. It presents the advantage of possessinga semantic layer, which should ease the extraction of domainspecificcorpora. Yet, as the Wikipedia category graph is scalefree,it can not be used as it is for these purposes. In this paper, wepropose a novel approach to graph clustering called BorderFlow,which we use and evaluate on the Wikipedia category graph.Additional possible applications of these results in the area ofinformation retrieval are presented. 2009 artículo científico 1870-9044 https://www.redalyc.org/articulo.oa?id=402640452001 en http://www.redalyc.org/revista.oa?id=4026 Polibits application/pdf Instituto Politécnico Nacional Polibits (México) Vol.39 |
| format | Artículo científico |
| id | redalyc_402640452001 |
| institution | Redalyc |
| language | en |
| publishDate | 2009 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | Disentangling the Wikipedia Category Graph for Corpus Extraction Axel-Cyrille Ngonga Ngomo Computación corpus extraction local graph clustering Natural language processing Disentangling the Wikipedia Category Graph for Corpus Extraction Axel-Cyrille Ngonga Ngomo Frank Schumacher Computación corpus extraction local graph clustering Natural language processing In several areas of research such as knowledgemanagement and natural language processing, domain-specificcorpora are required for tasks such as terminology extraction andontology learning. The presented investigations herein are basedon the assumption that Wikipedia can be used for the purposeof corpus extraction. It presents the advantage of possessinga semantic layer, which should ease the extraction of domainspecificcorpora. Yet, as the Wikipedia category graph is scalefree,it can not be used as it is for these purposes. In this paper, wepropose a novel approach to graph clustering called BorderFlow,which we use and evaluate on the Wikipedia category graph.Additional possible applications of these results in the area ofinformation retrieval are presented. 2009 artículo científico 1870-9044 https://www.redalyc.org/articulo.oa?id=402640452001 en http://www.redalyc.org/revista.oa?id=4026 Polibits application/pdf Instituto Politécnico Nacional Polibits (México) Vol.39 |
| title | Disentangling the Wikipedia Category Graph for Corpus Extraction |
| topic | Computación corpus extraction local graph clustering Natural language processing |
| url | https://www.redalyc.org/articulo.oa?id=402640452001 |