Matches in SemOpenAlex for { <https://semopenalex.org/work/W2361310941> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2361310941 abstract "Relation extraction is a fundamental task in information extraction,which is to identify the semantic relationships between two entities in the text.In this paper,deep belief nets(DBN),which is a classifier of a combination of several unsupervised learning networks,named RBM(restricted Boltzmann machine) and a supervised learning network named BP(back-propagation),is presented to detect and classify the relationships among Chinese name entities.The RBM layers maintain as much information as possible when feature vectors are transferred to next layer.The BP layer is trained to classify the features generated by the last RBM layer.The experiments are conducted on the Automatic Content Extraction 2004 dataset.This paper proves that a character-based feature is more suitable for Chinese relation extraction than a word-based feature.In addition,the paper also performs a set of experiments to assess the Chinese relation extraction on different assumptions of an entity categorization feature.These experiments showed the comparison among models with correct entity types and imperfect entity type classified by DBN and without entity type.The results show that DBN is a successful approach in the high-dimensional-feature-space information extraction task.It outperforms state-of-the-art learning models such as SVM and back-propagation networks." @default.
- W2361310941 created "2016-06-24" @default.
- W2361310941 creator A5059922371 @default.
- W2361310941 date "2012-01-01" @default.
- W2361310941 modified "2023-09-24" @default.
- W2361310941 title "Chinese Relation Extraction Based on Deep Belief Nets" @default.
- W2361310941 hasPublicationYear "2012" @default.
- W2361310941 type Work @default.
- W2361310941 sameAs 2361310941 @default.
- W2361310941 citedByCount "0" @default.
- W2361310941 crossrefType "journal-article" @default.
- W2361310941 hasAuthorship W2361310941A5059922371 @default.
- W2361310941 hasConcept C108583219 @default.
- W2361310941 hasConcept C119857082 @default.
- W2361310941 hasConcept C124101348 @default.
- W2361310941 hasConcept C136389625 @default.
- W2361310941 hasConcept C153180895 @default.
- W2361310941 hasConcept C153604712 @default.
- W2361310941 hasConcept C154945302 @default.
- W2361310941 hasConcept C195807954 @default.
- W2361310941 hasConcept C199354608 @default.
- W2361310941 hasConcept C204321447 @default.
- W2361310941 hasConcept C25343380 @default.
- W2361310941 hasConcept C41008148 @default.
- W2361310941 hasConcept C50644808 @default.
- W2361310941 hasConcept C52622490 @default.
- W2361310941 hasConcept C94124525 @default.
- W2361310941 hasConcept C95623464 @default.
- W2361310941 hasConcept C97385483 @default.
- W2361310941 hasConceptScore W2361310941C108583219 @default.
- W2361310941 hasConceptScore W2361310941C119857082 @default.
- W2361310941 hasConceptScore W2361310941C124101348 @default.
- W2361310941 hasConceptScore W2361310941C136389625 @default.
- W2361310941 hasConceptScore W2361310941C153180895 @default.
- W2361310941 hasConceptScore W2361310941C153604712 @default.
- W2361310941 hasConceptScore W2361310941C154945302 @default.
- W2361310941 hasConceptScore W2361310941C195807954 @default.
- W2361310941 hasConceptScore W2361310941C199354608 @default.
- W2361310941 hasConceptScore W2361310941C204321447 @default.
- W2361310941 hasConceptScore W2361310941C25343380 @default.
- W2361310941 hasConceptScore W2361310941C41008148 @default.
- W2361310941 hasConceptScore W2361310941C50644808 @default.
- W2361310941 hasConceptScore W2361310941C52622490 @default.
- W2361310941 hasConceptScore W2361310941C94124525 @default.
- W2361310941 hasConceptScore W2361310941C95623464 @default.
- W2361310941 hasConceptScore W2361310941C97385483 @default.
- W2361310941 hasLocation W23613109411 @default.
- W2361310941 hasOpenAccess W2361310941 @default.
- W2361310941 hasPrimaryLocation W23613109411 @default.
- W2361310941 hasRelatedWork W1673033330 @default.
- W2361310941 hasRelatedWork W173014460 @default.
- W2361310941 hasRelatedWork W1768856493 @default.
- W2361310941 hasRelatedWork W1951059531 @default.
- W2361310941 hasRelatedWork W1964812476 @default.
- W2361310941 hasRelatedWork W2000469266 @default.
- W2361310941 hasRelatedWork W2045817307 @default.
- W2361310941 hasRelatedWork W2124895976 @default.
- W2361310941 hasRelatedWork W2202931857 @default.
- W2361310941 hasRelatedWork W2480353959 @default.
- W2361310941 hasRelatedWork W2577073647 @default.
- W2361310941 hasRelatedWork W2757039741 @default.
- W2361310941 hasRelatedWork W2765183969 @default.
- W2361310941 hasRelatedWork W2912034626 @default.
- W2361310941 hasRelatedWork W2952208131 @default.
- W2361310941 hasRelatedWork W3009033882 @default.
- W2361310941 hasRelatedWork W3015801892 @default.
- W2361310941 hasRelatedWork W3081040224 @default.
- W2361310941 hasRelatedWork W3207997603 @default.
- W2361310941 hasRelatedWork W348043574 @default.
- W2361310941 isParatext "false" @default.
- W2361310941 isRetracted "false" @default.
- W2361310941 magId "2361310941" @default.
- W2361310941 workType "article" @default.