Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387344231> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4387344231 endingPage "470" @default.
- W4387344231 startingPage "470" @default.
- W4387344231 abstract "In recent years, machine learning approaches, in particular graph learning methods, have achieved great results in the field of natural language processing, in particular text classification tasks. However, many of such models have shown limited generalization on datasets in different languages. In this research, we investigate and elaborate graph machine learning methods on non-English datasets (such as the Persian Digikala dataset), which consists of users’ opinions for the task of text classification. More specifically, we investigate different combinations of (Pars) BERT with various graph neural network (GNN) architectures (such as GCN, GAT, and GIN) as well as use ensemble learning methods in order to tackle the text classification task on certain well-known non-English datasets. Our analysis and results demonstrate how applying GNN models helps in achieving good scores on the task of text classification by better capturing the topological information between textual data. Additionally, our experiments show how models employing language-specific pre-trained models (like ParsBERT, instead of BERT) capture better information about the data, resulting in better accuracies." @default.
- W4387344231 created "2023-10-05" @default.
- W4387344231 creator A5051159072 @default.
- W4387344231 creator A5058583486 @default.
- W4387344231 creator A5063626517 @default.
- W4387344231 creator A5068197413 @default.
- W4387344231 date "2023-10-04" @default.
- W4387344231 modified "2023-10-06" @default.
- W4387344231 title "On Enhancement of Text Classification and Analysis of Text Emotions Using Graph Machine Learning and Ensemble Learning Methods on Non-English Datasets" @default.
- W4387344231 cites W1832693441 @default.
- W4387344231 cites W1978394996 @default.
- W4387344231 cites W2064675550 @default.
- W4387344231 cites W2070232376 @default.
- W4387344231 cites W2143545157 @default.
- W4387344231 cites W2265846598 @default.
- W4387344231 cites W2726375170 @default.
- W4387344231 cites W2808129629 @default.
- W4387344231 cites W2945827377 @default.
- W4387344231 cites W2963355447 @default.
- W4387344231 cites W2964236337 @default.
- W4387344231 cites W2980718707 @default.
- W4387344231 cites W2985331920 @default.
- W4387344231 cites W3107770647 @default.
- W4387344231 cites W3173753074 @default.
- W4387344231 cites W3204526376 @default.
- W4387344231 cites W3213097325 @default.
- W4387344231 cites W4236122429 @default.
- W4387344231 doi "https://doi.org/10.3390/a16100470" @default.
- W4387344231 hasPublicationYear "2023" @default.
- W4387344231 type Work @default.
- W4387344231 citedByCount "0" @default.
- W4387344231 crossrefType "journal-article" @default.
- W4387344231 hasAuthorship W4387344231A5051159072 @default.
- W4387344231 hasAuthorship W4387344231A5058583486 @default.
- W4387344231 hasAuthorship W4387344231A5063626517 @default.
- W4387344231 hasAuthorship W4387344231A5068197413 @default.
- W4387344231 hasBestOaLocation W43873442311 @default.
- W4387344231 hasConcept C119857082 @default.
- W4387344231 hasConcept C132525143 @default.
- W4387344231 hasConcept C134306372 @default.
- W4387344231 hasConcept C154945302 @default.
- W4387344231 hasConcept C162324750 @default.
- W4387344231 hasConcept C177148314 @default.
- W4387344231 hasConcept C187736073 @default.
- W4387344231 hasConcept C204321447 @default.
- W4387344231 hasConcept C2780451532 @default.
- W4387344231 hasConcept C33923547 @default.
- W4387344231 hasConcept C41008148 @default.
- W4387344231 hasConcept C45942800 @default.
- W4387344231 hasConcept C50644808 @default.
- W4387344231 hasConcept C66945725 @default.
- W4387344231 hasConcept C71472368 @default.
- W4387344231 hasConcept C80444323 @default.
- W4387344231 hasConceptScore W4387344231C119857082 @default.
- W4387344231 hasConceptScore W4387344231C132525143 @default.
- W4387344231 hasConceptScore W4387344231C134306372 @default.
- W4387344231 hasConceptScore W4387344231C154945302 @default.
- W4387344231 hasConceptScore W4387344231C162324750 @default.
- W4387344231 hasConceptScore W4387344231C177148314 @default.
- W4387344231 hasConceptScore W4387344231C187736073 @default.
- W4387344231 hasConceptScore W4387344231C204321447 @default.
- W4387344231 hasConceptScore W4387344231C2780451532 @default.
- W4387344231 hasConceptScore W4387344231C33923547 @default.
- W4387344231 hasConceptScore W4387344231C41008148 @default.
- W4387344231 hasConceptScore W4387344231C45942800 @default.
- W4387344231 hasConceptScore W4387344231C50644808 @default.
- W4387344231 hasConceptScore W4387344231C66945725 @default.
- W4387344231 hasConceptScore W4387344231C71472368 @default.
- W4387344231 hasConceptScore W4387344231C80444323 @default.
- W4387344231 hasIssue "10" @default.
- W4387344231 hasLocation W43873442311 @default.
- W4387344231 hasOpenAccess W4387344231 @default.
- W4387344231 hasPrimaryLocation W43873442311 @default.
- W4387344231 hasRelatedWork W2075157159 @default.
- W4387344231 hasRelatedWork W2810053714 @default.
- W4387344231 hasRelatedWork W3136979370 @default.
- W4387344231 hasRelatedWork W4281560664 @default.
- W4387344231 hasRelatedWork W4281757034 @default.
- W4387344231 hasRelatedWork W4285046548 @default.
- W4387344231 hasRelatedWork W4285741730 @default.
- W4387344231 hasRelatedWork W4311847748 @default.
- W4387344231 hasRelatedWork W4313488044 @default.
- W4387344231 hasRelatedWork W4318350883 @default.
- W4387344231 hasVolume "16" @default.
- W4387344231 isParatext "false" @default.
- W4387344231 isRetracted "false" @default.
- W4387344231 workType "article" @default.