Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201378203> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3201378203 abstract "Natural Language Processing models have been increasingly used for many tasks, from sentiment analysis to text summarization. Most of these models are reaching the performance of human experts. Unfortunately, not only are these models not intuitive to the end-user, but they are also not even interpretable to highly-skilled Machine Learning scientists. We need explainable artificial intelligence to be able to trust models in high-stakes scenarios, and also to develop insights to optimize them by removing existing limitations and biases. In this paper, we devise a new tool called “Prediction Slope” that can be applied to any NLP model, extracting the importance rate of the component words and thereby helping to explain the model. It uses the average effect each word has on the final prediction slope as the word importance rate. We compared our technique with preceding approaches and observed that although they perform similarly, the earlier approaches do not generalize as well. Our method is independent of the model’s architecture and details." @default.
- W3201378203 created "2021-09-27" @default.
- W3201378203 creator A5014357711 @default.
- W3201378203 creator A5058549060 @default.
- W3201378203 date "2021-01-01" @default.
- W3201378203 modified "2023-09-26" @default.
- W3201378203 title "Deep NLP Explainer: Using Prediction Slope to Explain NLP Models" @default.
- W3201378203 cites W1787224781 @default.
- W3201378203 cites W1832693441 @default.
- W3201378203 cites W1849277567 @default.
- W3201378203 cites W2064675550 @default.
- W3201378203 cites W2120615054 @default.
- W3201378203 cites W2250539671 @default.
- W3201378203 cites W2282821441 @default.
- W3201378203 cites W2561412020 @default.
- W3201378203 cites W2657631929 @default.
- W3201378203 cites W2891503716 @default.
- W3201378203 cites W2914942835 @default.
- W3201378203 cites W2963039693 @default.
- W3201378203 cites W2963451564 @default.
- W3201378203 cites W2963495494 @default.
- W3201378203 cites W2964159778 @default.
- W3201378203 cites W2972526684 @default.
- W3201378203 cites W2996061341 @default.
- W3201378203 cites W3126960031 @default.
- W3201378203 cites W3127584900 @default.
- W3201378203 doi "https://doi.org/10.1007/978-3-030-86340-1_36" @default.
- W3201378203 hasPublicationYear "2021" @default.
- W3201378203 type Work @default.
- W3201378203 sameAs 3201378203 @default.
- W3201378203 citedByCount "1" @default.
- W3201378203 countsByYear W32013782032022 @default.
- W3201378203 crossrefType "book-chapter" @default.
- W3201378203 hasAuthorship W3201378203A5014357711 @default.
- W3201378203 hasAuthorship W3201378203A5058549060 @default.
- W3201378203 hasConcept C119857082 @default.
- W3201378203 hasConcept C121332964 @default.
- W3201378203 hasConcept C137293760 @default.
- W3201378203 hasConcept C138885662 @default.
- W3201378203 hasConcept C154945302 @default.
- W3201378203 hasConcept C168167062 @default.
- W3201378203 hasConcept C170858558 @default.
- W3201378203 hasConcept C195324797 @default.
- W3201378203 hasConcept C204321447 @default.
- W3201378203 hasConcept C2779439875 @default.
- W3201378203 hasConcept C41008148 @default.
- W3201378203 hasConcept C41895202 @default.
- W3201378203 hasConcept C66402592 @default.
- W3201378203 hasConcept C90805587 @default.
- W3201378203 hasConcept C97355855 @default.
- W3201378203 hasConceptScore W3201378203C119857082 @default.
- W3201378203 hasConceptScore W3201378203C121332964 @default.
- W3201378203 hasConceptScore W3201378203C137293760 @default.
- W3201378203 hasConceptScore W3201378203C138885662 @default.
- W3201378203 hasConceptScore W3201378203C154945302 @default.
- W3201378203 hasConceptScore W3201378203C168167062 @default.
- W3201378203 hasConceptScore W3201378203C170858558 @default.
- W3201378203 hasConceptScore W3201378203C195324797 @default.
- W3201378203 hasConceptScore W3201378203C204321447 @default.
- W3201378203 hasConceptScore W3201378203C2779439875 @default.
- W3201378203 hasConceptScore W3201378203C41008148 @default.
- W3201378203 hasConceptScore W3201378203C41895202 @default.
- W3201378203 hasConceptScore W3201378203C66402592 @default.
- W3201378203 hasConceptScore W3201378203C90805587 @default.
- W3201378203 hasConceptScore W3201378203C97355855 @default.
- W3201378203 hasLocation W32013782031 @default.
- W3201378203 hasOpenAccess W3201378203 @default.
- W3201378203 hasPrimaryLocation W32013782031 @default.
- W3201378203 hasRelatedWork W11133913 @default.
- W3201378203 hasRelatedWork W13780460 @default.
- W3201378203 hasRelatedWork W14230040 @default.
- W3201378203 hasRelatedWork W1563810 @default.
- W3201378203 hasRelatedWork W17684 @default.
- W3201378203 hasRelatedWork W4629839 @default.
- W3201378203 hasRelatedWork W5274612 @default.
- W3201378203 hasRelatedWork W7737393 @default.
- W3201378203 hasRelatedWork W8671328 @default.
- W3201378203 hasRelatedWork W13002482 @default.
- W3201378203 isParatext "false" @default.
- W3201378203 isRetracted "false" @default.
- W3201378203 magId "3201378203" @default.
- W3201378203 workType "book-chapter" @default.