Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225589039> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4225589039 endingPage "626" @default.
- W4225589039 startingPage "613" @default.
- W4225589039 abstract "Text classification is a fundamental Natural Language Processing task that has a wide variety of applications, where deep learning approaches have produced state-of-the-art results. While these models have been heavily criticized for their black-box nature, their robustness to slight perturbations in input text has been a matter of concern. In this work, we carry out a data-focused study evaluating the impact of systematic practical perturbations on the performance of the deep learning based text classification models like CNN, LSTM, and BERT-based algorithms. The perturbations are induced by the addition and removal of unwanted tokens like punctuation and stop-words that are minimally associated with the final performance of the model. We show that these deep learning approaches including BERT are sensitive to such legitimate input perturbations on four standard benchmark datasets SST2, TREC-6, BBC News, and tweet_eval. We observe that BERT is more susceptible to the removal of tokens as compared to the addition of tokens. Moreover, LSTM is slightly more sensitive to input perturbations as compared to CNN based model. The work also serves as a practical guide to assessing the impact of discrepancies in train-test conditions on the final performance of models." @default.
- W4225589039 created "2022-05-05" @default.
- W4225589039 creator A5009725385 @default.
- W4225589039 creator A5012950525 @default.
- W4225589039 creator A5045569782 @default.
- W4225589039 creator A5089921779 @default.
- W4225589039 date "2022-01-01" @default.
- W4225589039 modified "2023-10-03" @default.
- W4225589039 title "On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations" @default.
- W4225589039 cites W1932198206 @default.
- W4225589039 cites W2090805977 @default.
- W4225589039 cites W2240884068 @default.
- W4225589039 cites W2753546666 @default.
- W4225589039 cites W2962818281 @default.
- W4225589039 cites W2963908732 @default.
- W4225589039 cites W2996851481 @default.
- W4225589039 cites W3021743785 @default.
- W4225589039 cites W3034917890 @default.
- W4225589039 cites W3035507081 @default.
- W4225589039 cites W3088181395 @default.
- W4225589039 cites W3099215402 @default.
- W4225589039 cites W3101287165 @default.
- W4225589039 cites W3104382433 @default.
- W4225589039 cites W3105625590 @default.
- W4225589039 cites W3120414199 @default.
- W4225589039 cites W3120502588 @default.
- W4225589039 cites W3128611016 @default.
- W4225589039 cites W3172794097 @default.
- W4225589039 cites W3174354963 @default.
- W4225589039 cites W3176683285 @default.
- W4225589039 cites W3182965314 @default.
- W4225589039 cites W3198690080 @default.
- W4225589039 cites W4213059241 @default.
- W4225589039 doi "https://doi.org/10.1007/978-3-031-10464-0_42" @default.
- W4225589039 hasPublicationYear "2022" @default.
- W4225589039 type Work @default.
- W4225589039 citedByCount "2" @default.
- W4225589039 countsByYear W42255890392023 @default.
- W4225589039 crossrefType "book-chapter" @default.
- W4225589039 hasAuthorship W4225589039A5009725385 @default.
- W4225589039 hasAuthorship W4225589039A5012950525 @default.
- W4225589039 hasAuthorship W4225589039A5045569782 @default.
- W4225589039 hasAuthorship W4225589039A5089921779 @default.
- W4225589039 hasBestOaLocation W42255890392 @default.
- W4225589039 hasConcept C104317684 @default.
- W4225589039 hasConcept C108583219 @default.
- W4225589039 hasConcept C11413529 @default.
- W4225589039 hasConcept C119857082 @default.
- W4225589039 hasConcept C13280743 @default.
- W4225589039 hasConcept C154945302 @default.
- W4225589039 hasConcept C185592680 @default.
- W4225589039 hasConcept C185798385 @default.
- W4225589039 hasConcept C204321447 @default.
- W4225589039 hasConcept C205649164 @default.
- W4225589039 hasConcept C2984842247 @default.
- W4225589039 hasConcept C41008148 @default.
- W4225589039 hasConcept C540372491 @default.
- W4225589039 hasConcept C55493867 @default.
- W4225589039 hasConcept C63479239 @default.
- W4225589039 hasConceptScore W4225589039C104317684 @default.
- W4225589039 hasConceptScore W4225589039C108583219 @default.
- W4225589039 hasConceptScore W4225589039C11413529 @default.
- W4225589039 hasConceptScore W4225589039C119857082 @default.
- W4225589039 hasConceptScore W4225589039C13280743 @default.
- W4225589039 hasConceptScore W4225589039C154945302 @default.
- W4225589039 hasConceptScore W4225589039C185592680 @default.
- W4225589039 hasConceptScore W4225589039C185798385 @default.
- W4225589039 hasConceptScore W4225589039C204321447 @default.
- W4225589039 hasConceptScore W4225589039C205649164 @default.
- W4225589039 hasConceptScore W4225589039C2984842247 @default.
- W4225589039 hasConceptScore W4225589039C41008148 @default.
- W4225589039 hasConceptScore W4225589039C540372491 @default.
- W4225589039 hasConceptScore W4225589039C55493867 @default.
- W4225589039 hasConceptScore W4225589039C63479239 @default.
- W4225589039 hasLocation W42255890391 @default.
- W4225589039 hasLocation W42255890392 @default.
- W4225589039 hasOpenAccess W4225589039 @default.
- W4225589039 hasPrimaryLocation W42255890391 @default.
- W4225589039 hasRelatedWork W3014300295 @default.
- W4225589039 hasRelatedWork W3164822677 @default.
- W4225589039 hasRelatedWork W4223943233 @default.
- W4225589039 hasRelatedWork W4225161397 @default.
- W4225589039 hasRelatedWork W4288040045 @default.
- W4225589039 hasRelatedWork W4312200629 @default.
- W4225589039 hasRelatedWork W4360585206 @default.
- W4225589039 hasRelatedWork W4364306694 @default.
- W4225589039 hasRelatedWork W4380075502 @default.
- W4225589039 hasRelatedWork W4380086463 @default.
- W4225589039 isParatext "false" @default.
- W4225589039 isRetracted "false" @default.
- W4225589039 workType "book-chapter" @default.