FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176176306> ?p ?o ?g. }

• W3176176306 abstract "While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data. Such issues come to be manifest in performance problems when faced with out-of-distribution data in the field. One recent solution has been to use counterfactually augmented datasets in order to reduce any reliance on spurious patterns that may exist in the original data. Producing high-quality augmented data can be costly and time-consuming as it usually needs to involve human feedback and crowdsourcing efforts. In this work, we propose an alternative by describing and evaluating an approach to automatically generating counterfactual data for data augmentation and explanation. A comprehensive evaluation on several different datasets and using a variety of state-of-the-art benchmarks demonstrate how our approach can achieve significant improvements in model performance when compared to models training on the original data and even when compared to models trained with the benefit of human-generated augmented data." @default.
• W3176176306 created "2021-07-05" @default.
• W3176176306 creator A5009000289 @default.
• W3176176306 creator A5010776860 @default.
• W3176176306 creator A5016056973 @default.
• W3176176306 creator A5035082722 @default.
• W3176176306 creator A5059144722 @default.
• W3176176306 creator A5065595661 @default.
• W3176176306 date "2021-06-29" @default.
• W3176176306 modified "2023-09-25" @default.
• W3176176306 title "Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis" @default.
• W3176176306 cites W1493730910 @default.
• W3176176306 cites W1596717185 @default.
• W3176176306 cites W2051840895 @default.
• W3176176306 cites W2108646579 @default.
• W3176176306 cites W2112422413 @default.
• W3176176306 cites W2113459411 @default.
• W3176176306 cites W2160660844 @default.
• W3176176306 cites W2162651021 @default.
• W3176176306 cites W2282821441 @default.
• W3176176306 cites W2470673105 @default.
• W3176176306 cites W2740721704 @default.
• W3176176306 cites W2774616426 @default.
• W3176176306 cites W2916132663 @default.
• W3176176306 cites W2948194985 @default.
• W3176176306 cites W2950606982 @default.
• W3176176306 cites W2950866572 @default.
• W3176176306 cites W2952280064 @default.
• W3176176306 cites W2962790223 @default.
• W3176176306 cites W2962862931 @default.
• W3176176306 cites W2963095307 @default.
• W3176176306 cites W2963341956 @default.
• W3176176306 cites W2963403868 @default.
• W3176176306 cites W2963420481 @default.
• W3176176306 cites W2963963281 @default.
• W3176176306 cites W2965373594 @default.
• W3176176306 cites W2965970765 @default.
• W3176176306 cites W2966362896 @default.
• W3176176306 cites W2970562804 @default.
• W3176176306 cites W2970597249 @default.
• W3176176306 cites W2970785793 @default.
• W3176176306 cites W2971015127 @default.
• W3176176306 cites W2971196067 @default.
• W3176176306 cites W2983693488 @default.
• W3176176306 cites W2994934025 @default.
• W3176176306 cites W2996507500 @default.
• W3176176306 cites W2996728628 @default.
• W3176176306 cites W3005086430 @default.
• W3176176306 cites W3017038769 @default.
• W3176176306 cites W3032150215 @default.
• W3176176306 cites W3034319502 @default.
• W3176176306 cites W3034723486 @default.
• W3176176306 cites W3035422656 @default.
• W3176176306 cites W3035507081 @default.
• W3176176306 cites W3035736465 @default.
• W3176176306 cites W3089631405 @default.
• W3176176306 cites W3094475872 @default.
• W3176176306 cites W3096942073 @default.
• W3176176306 cites W3106031848 @default.
• W3176176306 cites W3114925695 @default.
• W3176176306 cites W3115467802 @default.
• W3176176306 cites W3115848884 @default.
• W3176176306 cites W3123959279 @default.
• W3176176306 cites W3128232076 @default.
• W3176176306 cites W3175172065 @default.
• W3176176306 cites W3177397812 @default.
• W3176176306 cites W3023071679 @default.
• W3176176306 cites W3048400930 @default.
• W3176176306 doi "https://doi.org/10.48550/arxiv.2106.15231" @default.
• W3176176306 hasPublicationYear "2021" @default.
• W3176176306 type Work @default.
• W3176176306 sameAs 3176176306 @default.
• W3176176306 citedByCount "0" @default.
• W3176176306 crossrefType "posted-content" @default.
• W3176176306 hasAuthorship W3176176306A5009000289 @default.
• W3176176306 hasAuthorship W3176176306A5010776860 @default.
• W3176176306 hasAuthorship W3176176306A5016056973 @default.
• W3176176306 hasAuthorship W3176176306A5035082722 @default.
• W3176176306 hasAuthorship W3176176306A5059144722 @default.
• W3176176306 hasAuthorship W3176176306A5065595661 @default.
• W3176176306 hasBestOaLocation W31761763061 @default.
• W3176176306 hasConcept C104317684 @default.
• W3176176306 hasConcept C108650721 @default.
• W3176176306 hasConcept C111472728 @default.
• W3176176306 hasConcept C119857082 @default.
• W3176176306 hasConcept C124101348 @default.
• W3176176306 hasConcept C127413603 @default.
• W3176176306 hasConcept C136197465 @default.
• W3176176306 hasConcept C136764020 @default.
• W3176176306 hasConcept C138885662 @default.
• W3176176306 hasConcept C154945302 @default.
• W3176176306 hasConcept C176217482 @default.
• W3176176306 hasConcept C185592680 @default.
• W3176176306 hasConcept C202444582 @default.
• W3176176306 hasConcept C21547014 @default.
• W3176176306 hasConcept C24756922 @default.
• W3176176306 hasConcept C2522767166 @default.
• W3176176306 hasConcept C33923547 @default.
• W3176176306 hasConcept C41008148 @default.
• W3176176306 hasConcept C55493867 @default.

• next