FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200524025> ?p ?o ?g. }

• W3200524025 abstract "This paper investigates continual learning for semantic parsing. In this setting, a neural semantic parser learns tasks sequentially without accessing full training data from previous tasks. Direct application of the SOTA continual learning algorithms to this problem fails to achieve comparable performance with re-training models with all seen tasks because they have not considered the special properties of structured outputs yielded by semantic parsers. Therefore, we propose TotalRecall, a continual learning method designed for neural semantic parsers from two aspects: i) a sampling method for memory replay that diversifies logical form templates and balances distributions of parse actions in a memory; ii) a two-stage training method that significantly improves generalization capability of the parsers across tasks. We conduct extensive experiments to study the research problems involved in continual semantic parsing and demonstrate that a neural semantic parser trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch." @default.
• W3200524025 created "2021-09-27" @default.
• W3200524025 creator A5008486397 @default.
• W3200524025 creator A5047839791 @default.
• W3200524025 creator A5081525024 @default.
• W3200524025 date "2021-01-01" @default.
• W3200524025 modified "2023-10-16" @default.
• W3200524025 title "Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers" @default.
• W3200524025 cites W1522301498 @default.
• W3200524025 cites W1821462560 @default.
• W3200524025 cites W1881549354 @default.
• W3200524025 cites W1902237438 @default.
• W3200524025 cites W2064675550 @default.
• W3200524025 cites W2083620785 @default.
• W3200524025 cites W2130942839 @default.
• W3200524025 cites W2164724958 @default.
• W3200524025 cites W2250375035 @default.
• W3200524025 cites W2250539671 @default.
• W3200524025 cites W2251957808 @default.
• W3200524025 cites W2252123671 @default.
• W3200524025 cites W2473930607 @default.
• W3200524025 cites W2560647685 @default.
• W3200524025 cites W2601450892 @default.
• W3200524025 cites W2737492962 @default.
• W3200524025 cites W2890867094 @default.
• W3200524025 cites W2899496522 @default.
• W3200524025 cites W2903190877 @default.
• W3200524025 cites W2945102109 @default.
• W3200524025 cites W2947354947 @default.
• W3200524025 cites W2947461406 @default.
• W3200524025 cites W2950869915 @default.
• W3200524025 cites W2951790836 @default.
• W3200524025 cites W2953494151 @default.
• W3200524025 cites W2955270045 @default.
• W3200524025 cites W2962724315 @default.
• W3200524025 cites W2962884963 @default.
• W3200524025 cites W2963003887 @default.
• W3200524025 cites W2963072899 @default.
• W3200524025 cites W2963341956 @default.
• W3200524025 cites W2963357517 @default.
• W3200524025 cites W2963393617 @default.
• W3200524025 cites W2963733234 @default.
• W3200524025 cites W2963794306 @default.
• W3200524025 cites W2963813679 @default.
• W3200524025 cites W2963844079 @default.
• W3200524025 cites W2963850662 @default.
• W3200524025 cites W2963960541 @default.
• W3200524025 cites W2964189064 @default.
• W3200524025 cites W2964271186 @default.
• W3200524025 cites W2964303773 @default.
• W3200524025 cites W2966755025 @default.
• W3200524025 cites W2970066656 @default.
• W3200524025 cites W2970393840 @default.
• W3200524025 cites W2970490744 @default.
• W3200524025 cites W2971291256 @default.
• W3200524025 cites W2971910751 @default.
• W3200524025 cites W3002800333 @default.
• W3200524025 cites W3003289092 @default.
• W3200524025 cites W3005441132 @default.
• W3200524025 cites W3034835156 @default.
• W3200524025 cites W3034856281 @default.
• W3200524025 cites W3035471260 @default.
• W3200524025 cites W3035691277 @default.
• W3200524025 cites W3100152912 @default.
• W3200524025 cites W3100156920 @default.
• W3200524025 cites W3103469330 @default.
• W3200524025 cites W3108981297 @default.
• W3200524025 cites W3110148193 @default.
• W3200524025 cites W3115585256 @default.
• W3200524025 cites W3137214344 @default.
• W3200524025 cites W3153675281 @default.
• W3200524025 cites W3154977041 @default.
• W3200524025 doi "https://doi.org/10.18653/v1/2021.emnlp-main.310" @default.
• W3200524025 hasPublicationYear "2021" @default.
• W3200524025 type Work @default.
• W3200524025 sameAs 3200524025 @default.
• W3200524025 citedByCount "2" @default.
• W3200524025 countsByYear W32005240252023 @default.
• W3200524025 crossrefType "proceedings-article" @default.
• W3200524025 hasAuthorship W3200524025A5008486397 @default.
• W3200524025 hasAuthorship W3200524025A5047839791 @default.
• W3200524025 hasAuthorship W3200524025A5081525024 @default.
• W3200524025 hasBestOaLocation W32005240251 @default.
• W3200524025 hasConcept C119857082 @default.
• W3200524025 hasConcept C134306372 @default.
• W3200524025 hasConcept C154945302 @default.
• W3200524025 hasConcept C173608175 @default.
• W3200524025 hasConcept C177148314 @default.
• W3200524025 hasConcept C186644900 @default.
• W3200524025 hasConcept C204321447 @default.
• W3200524025 hasConcept C33923547 @default.
• W3200524025 hasConcept C41008148 @default.
• W3200524025 hasConcept C50644808 @default.
• W3200524025 hasConcept C68339613 @default.
• W3200524025 hasConceptScore W3200524025C119857082 @default.
• W3200524025 hasConceptScore W3200524025C134306372 @default.
• W3200524025 hasConceptScore W3200524025C154945302 @default.
• W3200524025 hasConceptScore W3200524025C173608175 @default.
• W3200524025 hasConceptScore W3200524025C177148314 @default.
• W3200524025 hasConceptScore W3200524025C186644900 @default.

• next