Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206299105> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4206299105 endingPage "1" @default.
- W4206299105 startingPage "1" @default.
- W4206299105 abstract "The biggest challenge of building chatbots is training data. The required data must be realistic and large enough to train chatbots. We create a tool to get actual training data from Facebook messenger of a Facebook page. After text preprocessing steps, the newly obtained dataset generates FVnC and Sample dataset. We use the Retraining of BERT for Vietnamese (PhoBERT) to extract features of our text data. K-Means and DBSCAN clustering algorithms are used for clustering tasks based on output embeddings from PhoBERT$_{base}$. We apply V-measure score and Silhouette score to evaluate the performance of clustering algorithms. We also demonstrate the efficiency of PhoBERT compared to other models in feature extraction on the Sample dataset and wiki dataset. A GridSearch algorithm that combines both clustering evaluations is also proposed to find optimal parameters. Thanks to clustering such a number of conversations, we save a lot of time and effort to build data and storylines for training chatbot." @default.
- W4206299105 created "2022-01-26" @default.
- W4206299105 creator A5006072946 @default.
- W4206299105 creator A5019384763 @default.
- W4206299105 creator A5026176200 @default.
- W4206299105 creator A5059611428 @default.
- W4206299105 date "2022-01-01" @default.
- W4206299105 modified "2023-09-27" @default.
- W4206299105 title "CLUSTERING VIETNAMESE CONVERSATIONS FROM FACEBOOK PAGE TO BUILD TRAINING DATASET FOR CHATBOT" @default.
- W4206299105 doi "https://doi.org/10.5455/jjcit.71-1632557439" @default.
- W4206299105 hasPublicationYear "2022" @default.
- W4206299105 type Work @default.
- W4206299105 citedByCount "0" @default.
- W4206299105 crossrefType "journal-article" @default.
- W4206299105 hasAuthorship W4206299105A5006072946 @default.
- W4206299105 hasAuthorship W4206299105A5019384763 @default.
- W4206299105 hasAuthorship W4206299105A5026176200 @default.
- W4206299105 hasAuthorship W4206299105A5059611428 @default.
- W4206299105 hasBestOaLocation W42062991051 @default.
- W4206299105 hasConcept C10551718 @default.
- W4206299105 hasConcept C119857082 @default.
- W4206299105 hasConcept C124101348 @default.
- W4206299105 hasConcept C144133560 @default.
- W4206299105 hasConcept C154945302 @default.
- W4206299105 hasConcept C155202549 @default.
- W4206299105 hasConcept C17212007 @default.
- W4206299105 hasConcept C185592680 @default.
- W4206299105 hasConcept C198531522 @default.
- W4206299105 hasConcept C23123220 @default.
- W4206299105 hasConcept C2778712577 @default.
- W4206299105 hasConcept C2779041454 @default.
- W4206299105 hasConcept C33704608 @default.
- W4206299105 hasConcept C34736171 @default.
- W4206299105 hasConcept C41008148 @default.
- W4206299105 hasConcept C43617362 @default.
- W4206299105 hasConcept C46576248 @default.
- W4206299105 hasConcept C73555534 @default.
- W4206299105 hasConceptScore W4206299105C10551718 @default.
- W4206299105 hasConceptScore W4206299105C119857082 @default.
- W4206299105 hasConceptScore W4206299105C124101348 @default.
- W4206299105 hasConceptScore W4206299105C144133560 @default.
- W4206299105 hasConceptScore W4206299105C154945302 @default.
- W4206299105 hasConceptScore W4206299105C155202549 @default.
- W4206299105 hasConceptScore W4206299105C17212007 @default.
- W4206299105 hasConceptScore W4206299105C185592680 @default.
- W4206299105 hasConceptScore W4206299105C198531522 @default.
- W4206299105 hasConceptScore W4206299105C23123220 @default.
- W4206299105 hasConceptScore W4206299105C2778712577 @default.
- W4206299105 hasConceptScore W4206299105C2779041454 @default.
- W4206299105 hasConceptScore W4206299105C33704608 @default.
- W4206299105 hasConceptScore W4206299105C34736171 @default.
- W4206299105 hasConceptScore W4206299105C41008148 @default.
- W4206299105 hasConceptScore W4206299105C43617362 @default.
- W4206299105 hasConceptScore W4206299105C46576248 @default.
- W4206299105 hasConceptScore W4206299105C73555534 @default.
- W4206299105 hasIssue "0" @default.
- W4206299105 hasLocation W42062991051 @default.
- W4206299105 hasLocation W42062991052 @default.
- W4206299105 hasLocation W42062991053 @default.
- W4206299105 hasLocation W42062991054 @default.
- W4206299105 hasOpenAccess W4206299105 @default.
- W4206299105 hasPrimaryLocation W42062991051 @default.
- W4206299105 hasRelatedWork W2107950767 @default.
- W4206299105 hasRelatedWork W2132602978 @default.
- W4206299105 hasRelatedWork W2132814129 @default.
- W4206299105 hasRelatedWork W2546959060 @default.
- W4206299105 hasRelatedWork W2766298719 @default.
- W4206299105 hasRelatedWork W3046546608 @default.
- W4206299105 hasRelatedWork W4210871448 @default.
- W4206299105 hasRelatedWork W4308143336 @default.
- W4206299105 hasRelatedWork W4309380876 @default.
- W4206299105 hasRelatedWork W2566086483 @default.
- W4206299105 isParatext "false" @default.
- W4206299105 isRetracted "false" @default.
- W4206299105 workType "article" @default.