Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046764523> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3046764523 abstract "Digital Libraries benefit from the use of text classification strategies since they are enablers for performing many document management tasks like Information Retrieval. The effectiveness of such classification strategies depends on the amount of available data and the classifier used. The former leads to the design of data augmentation solutions where new samples are generated into small datasets based on the semantic similarity between existing samples and concepts defined within external linguistic resources. The latter relates to the capability of finding, which is the best learning principle to adopt for designing an effective classification strategy suitable for the problem. In this work, we propose a neural-based architecture thought for addressing the text classification problem on small datasets. Our architecture is based on BERT equipped with one further layer using the sigmoid function. The hypothesis we want to verify is that by using embeddings learned by a BERT-based architecture, one can perform effective classification on small datasets without the use of data augmentation strategies. We observed improvements up to 14% in the accuracy and up to $23%$ in the f-score with respect to baseline classifiers exploiting data augmentation." @default.
- W3046764523 created "2020-08-07" @default.
- W3046764523 creator A5014398832 @default.
- W3046764523 creator A5051031973 @default.
- W3046764523 creator A5069303169 @default.
- W3046764523 date "2020-08-01" @default.
- W3046764523 modified "2023-09-23" @default.
- W3046764523 title "A Neural-based Architecture For Small Datasets Classification" @default.
- W3046764523 cites W1999337483 @default.
- W3046764523 cites W2068802535 @default.
- W3046764523 cites W2131912381 @default.
- W3046764523 cites W2250539671 @default.
- W3046764523 cites W2371227879 @default.
- W3046764523 cites W2786345542 @default.
- W3046764523 cites W2912253874 @default.
- W3046764523 cites W2946423414 @default.
- W3046764523 cites W2969112210 @default.
- W3046764523 cites W2981842822 @default.
- W3046764523 cites W2995253144 @default.
- W3046764523 doi "https://doi.org/10.1145/3383583.3398535" @default.
- W3046764523 hasPublicationYear "2020" @default.
- W3046764523 type Work @default.
- W3046764523 sameAs 3046764523 @default.
- W3046764523 citedByCount "1" @default.
- W3046764523 countsByYear W30467645232022 @default.
- W3046764523 crossrefType "proceedings-article" @default.
- W3046764523 hasAuthorship W3046764523A5014398832 @default.
- W3046764523 hasAuthorship W3046764523A5051031973 @default.
- W3046764523 hasAuthorship W3046764523A5069303169 @default.
- W3046764523 hasConcept C103278499 @default.
- W3046764523 hasConcept C115961682 @default.
- W3046764523 hasConcept C119857082 @default.
- W3046764523 hasConcept C123657996 @default.
- W3046764523 hasConcept C124101348 @default.
- W3046764523 hasConcept C14036430 @default.
- W3046764523 hasConcept C142362112 @default.
- W3046764523 hasConcept C153180895 @default.
- W3046764523 hasConcept C153349607 @default.
- W3046764523 hasConcept C154945302 @default.
- W3046764523 hasConcept C23123220 @default.
- W3046764523 hasConcept C2779280203 @default.
- W3046764523 hasConcept C41008148 @default.
- W3046764523 hasConcept C50644808 @default.
- W3046764523 hasConcept C78458016 @default.
- W3046764523 hasConcept C81388566 @default.
- W3046764523 hasConcept C86803240 @default.
- W3046764523 hasConcept C95623464 @default.
- W3046764523 hasConceptScore W3046764523C103278499 @default.
- W3046764523 hasConceptScore W3046764523C115961682 @default.
- W3046764523 hasConceptScore W3046764523C119857082 @default.
- W3046764523 hasConceptScore W3046764523C123657996 @default.
- W3046764523 hasConceptScore W3046764523C124101348 @default.
- W3046764523 hasConceptScore W3046764523C14036430 @default.
- W3046764523 hasConceptScore W3046764523C142362112 @default.
- W3046764523 hasConceptScore W3046764523C153180895 @default.
- W3046764523 hasConceptScore W3046764523C153349607 @default.
- W3046764523 hasConceptScore W3046764523C154945302 @default.
- W3046764523 hasConceptScore W3046764523C23123220 @default.
- W3046764523 hasConceptScore W3046764523C2779280203 @default.
- W3046764523 hasConceptScore W3046764523C41008148 @default.
- W3046764523 hasConceptScore W3046764523C50644808 @default.
- W3046764523 hasConceptScore W3046764523C78458016 @default.
- W3046764523 hasConceptScore W3046764523C81388566 @default.
- W3046764523 hasConceptScore W3046764523C86803240 @default.
- W3046764523 hasConceptScore W3046764523C95623464 @default.
- W3046764523 hasLocation W30467645231 @default.
- W3046764523 hasOpenAccess W3046764523 @default.
- W3046764523 hasPrimaryLocation W30467645231 @default.
- W3046764523 hasRelatedWork W2001652754 @default.
- W3046764523 hasRelatedWork W2349125667 @default.
- W3046764523 hasRelatedWork W2381176432 @default.
- W3046764523 hasRelatedWork W2549006548 @default.
- W3046764523 hasRelatedWork W2807311372 @default.
- W3046764523 hasRelatedWork W2961085424 @default.
- W3046764523 hasRelatedWork W3043252291 @default.
- W3046764523 hasRelatedWork W4214932115 @default.
- W3046764523 hasRelatedWork W1629725936 @default.
- W3046764523 hasRelatedWork W3158004940 @default.
- W3046764523 isParatext "false" @default.
- W3046764523 isRetracted "false" @default.
- W3046764523 magId "3046764523" @default.
- W3046764523 workType "article" @default.