Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196670497> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3196670497 abstract "Purpose: In order to use a popular supervised learning algorithm such as BERT to extract the relationships of concepts (triple relationship extraction), it is necessary to label the relationship types manually. If some relation words are not been labeled in the training stag, they cannot be recognized probably in the test stage and the corresponding entities cannot been recognized accordingly. This paper proposes a new unsupervised algorithm to extract as many relation words as possible of two entities, especially those that are easily overlooked. Methods: The disease-cause relationship was taken as an example, and 10204 effective sentences of disease and corresponding causes were extracted by web crawler. According to the constraints of syntactic, semantic and lexical features, the relationship words were extracted with an unsupervised manner, and the automatic extracted results were summarized. Results: Some specific relation words that are ignored in manual labeling stage are found; the conjoining relation words often appeared together in the texts are recognized; some types and features of relation words are obtained. These types and features can be used to help the relation labeling in the supervised learning stage, and to help expanding the relevant knowledge graphs and improving the accuracy of information retrieval." @default.
- W3196670497 created "2021-09-13" @default.
- W3196670497 creator A5001220661 @default.
- W3196670497 creator A5006032178 @default.
- W3196670497 creator A5022969296 @default.
- W3196670497 creator A5051020422 @default.
- W3196670497 date "2021-04-01" @default.
- W3196670497 modified "2023-09-23" @default.
- W3196670497 title "A new unsupervised Algorithm for extracting relationship words between two entities" @default.
- W3196670497 cites W2123143128 @default.
- W3196670497 cites W2132522721 @default.
- W3196670497 cites W2785321994 @default.
- W3196670497 doi "https://doi.org/10.1109/ctisc52352.2021.00037" @default.
- W3196670497 hasPublicationYear "2021" @default.
- W3196670497 type Work @default.
- W3196670497 sameAs 3196670497 @default.
- W3196670497 citedByCount "0" @default.
- W3196670497 crossrefType "proceedings-article" @default.
- W3196670497 hasAuthorship W3196670497A5001220661 @default.
- W3196670497 hasAuthorship W3196670497A5006032178 @default.
- W3196670497 hasAuthorship W3196670497A5022969296 @default.
- W3196670497 hasAuthorship W3196670497A5051020422 @default.
- W3196670497 hasConcept C119857082 @default.
- W3196670497 hasConcept C124101348 @default.
- W3196670497 hasConcept C153604712 @default.
- W3196670497 hasConcept C154945302 @default.
- W3196670497 hasConcept C169760540 @default.
- W3196670497 hasConcept C169900460 @default.
- W3196670497 hasConcept C195807954 @default.
- W3196670497 hasConcept C204321447 @default.
- W3196670497 hasConcept C25343380 @default.
- W3196670497 hasConcept C2988080768 @default.
- W3196670497 hasConcept C41008148 @default.
- W3196670497 hasConcept C86803240 @default.
- W3196670497 hasConceptScore W3196670497C119857082 @default.
- W3196670497 hasConceptScore W3196670497C124101348 @default.
- W3196670497 hasConceptScore W3196670497C153604712 @default.
- W3196670497 hasConceptScore W3196670497C154945302 @default.
- W3196670497 hasConceptScore W3196670497C169760540 @default.
- W3196670497 hasConceptScore W3196670497C169900460 @default.
- W3196670497 hasConceptScore W3196670497C195807954 @default.
- W3196670497 hasConceptScore W3196670497C204321447 @default.
- W3196670497 hasConceptScore W3196670497C25343380 @default.
- W3196670497 hasConceptScore W3196670497C2988080768 @default.
- W3196670497 hasConceptScore W3196670497C41008148 @default.
- W3196670497 hasConceptScore W3196670497C86803240 @default.
- W3196670497 hasLocation W31966704971 @default.
- W3196670497 hasOpenAccess W3196670497 @default.
- W3196670497 hasPrimaryLocation W31966704971 @default.
- W3196670497 hasRelatedWork W10015831 @default.
- W3196670497 hasRelatedWork W12678834 @default.
- W3196670497 hasRelatedWork W13618705 @default.
- W3196670497 hasRelatedWork W2864082 @default.
- W3196670497 hasRelatedWork W4518655 @default.
- W3196670497 hasRelatedWork W4930744 @default.
- W3196670497 hasRelatedWork W5192282 @default.
- W3196670497 hasRelatedWork W9321062 @default.
- W3196670497 hasRelatedWork W9770290 @default.
- W3196670497 hasRelatedWork W13673164 @default.
- W3196670497 isParatext "false" @default.
- W3196670497 isRetracted "false" @default.
- W3196670497 magId "3196670497" @default.
- W3196670497 workType "article" @default.