Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287643493> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4287643493 abstract "Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases) is hardly possible, many real-world text classifiers are trained on the available, yet imperfect, datasets. These classifiers are thus likely to have undesirable properties. For instance, they may have biases against some sub-populations or may not work effectively in the wild due to overfitting. In this paper, we propose FIND -- a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. Experiments show that by using FIND, humans can improve CNN text classifiers which were trained under different types of imperfect datasets (including datasets with biases and datasets with dissimilar train-test distributions)." @default.
- W4287643493 created "2022-07-25" @default.
- W4287643493 creator A5030347098 @default.
- W4287643493 creator A5053217291 @default.
- W4287643493 creator A5078354590 @default.
- W4287643493 date "2020-10-10" @default.
- W4287643493 modified "2023-09-28" @default.
- W4287643493 title "FIND: Human-in-the-Loop Debugging Deep Text Classifiers" @default.
- W4287643493 doi "https://doi.org/10.48550/arxiv.2010.04987" @default.
- W4287643493 hasPublicationYear "2020" @default.
- W4287643493 type Work @default.
- W4287643493 citedByCount "0" @default.
- W4287643493 crossrefType "posted-content" @default.
- W4287643493 hasAuthorship W4287643493A5030347098 @default.
- W4287643493 hasAuthorship W4287643493A5053217291 @default.
- W4287643493 hasAuthorship W4287643493A5078354590 @default.
- W4287643493 hasBestOaLocation W42876434931 @default.
- W4287643493 hasConcept C108583219 @default.
- W4287643493 hasConcept C119857082 @default.
- W4287643493 hasConcept C138885662 @default.
- W4287643493 hasConcept C154945302 @default.
- W4287643493 hasConcept C168065819 @default.
- W4287643493 hasConcept C199360897 @default.
- W4287643493 hasConcept C22019652 @default.
- W4287643493 hasConcept C2780310539 @default.
- W4287643493 hasConcept C41008148 @default.
- W4287643493 hasConcept C41895202 @default.
- W4287643493 hasConcept C50644808 @default.
- W4287643493 hasConceptScore W4287643493C108583219 @default.
- W4287643493 hasConceptScore W4287643493C119857082 @default.
- W4287643493 hasConceptScore W4287643493C138885662 @default.
- W4287643493 hasConceptScore W4287643493C154945302 @default.
- W4287643493 hasConceptScore W4287643493C168065819 @default.
- W4287643493 hasConceptScore W4287643493C199360897 @default.
- W4287643493 hasConceptScore W4287643493C22019652 @default.
- W4287643493 hasConceptScore W4287643493C2780310539 @default.
- W4287643493 hasConceptScore W4287643493C41008148 @default.
- W4287643493 hasConceptScore W4287643493C41895202 @default.
- W4287643493 hasConceptScore W4287643493C50644808 @default.
- W4287643493 hasLocation W42876434931 @default.
- W4287643493 hasLocation W42876434932 @default.
- W4287643493 hasLocation W42876434933 @default.
- W4287643493 hasOpenAccess W4287643493 @default.
- W4287643493 hasPrimaryLocation W42876434931 @default.
- W4287643493 hasRelatedWork W10202958 @default.
- W4287643493 hasRelatedWork W11562254 @default.
- W4287643493 hasRelatedWork W11919366 @default.
- W4287643493 hasRelatedWork W12793662 @default.
- W4287643493 hasRelatedWork W4275953 @default.
- W4287643493 hasRelatedWork W6229082 @default.
- W4287643493 hasRelatedWork W6680660 @default.
- W4287643493 hasRelatedWork W7303821 @default.
- W4287643493 hasRelatedWork W9190101 @default.
- W4287643493 hasRelatedWork W5829715 @default.
- W4287643493 isParatext "false" @default.
- W4287643493 isRetracted "false" @default.
- W4287643493 workType "article" @default.