FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100152912> ?p ?o ?g. }

• W3100152912 abstract "Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a “continual learning” setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on Elastic Weight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue." @default.
• W3100152912 created "2020-11-23" @default.
• W3100152912 creator A5012014905 @default.
• W3100152912 creator A5049682051 @default.
• W3100152912 creator A5058504936 @default.
• W3100152912 creator A5060427576 @default.
• W3100152912 creator A5071250011 @default.
• W3100152912 date "2020-01-01" @default.
• W3100152912 modified "2023-10-14" @default.
• W3100152912 title "Continual Learning for Natural Language Generation in Task-oriented Dialog Systems" @default.
• W3100152912 cites W1682403713 @default.
• W3100152912 cites W1821462560 @default.
• W3100152912 cites W1904365287 @default.
• W3100152912 cites W1948566616 @default.
• W3100152912 cites W1997865285 @default.
• W3100152912 cites W2060277733 @default.
• W3100152912 cites W2101105183 @default.
• W3100152912 cites W2473930607 @default.
• W3100152912 cites W2560647685 @default.
• W3100152912 cites W2737492962 @default.
• W3100152912 cites W2777054756 @default.
• W3100152912 cites W2879018339 @default.
• W3100152912 cites W2884282566 @default.
• W3100152912 cites W2888912057 @default.
• W3100152912 cites W2898790713 @default.
• W3100152912 cites W2911681509 @default.
• W3100152912 cites W2927746189 @default.
• W3100152912 cites W2945383715 @default.
• W3100152912 cites W2948734064 @default.
• W3100152912 cites W2950760213 @default.
• W3100152912 cites W2951176429 @default.
• W3100152912 cites W2951980657 @default.
• W3100152912 cites W2954929116 @default.
• W3100152912 cites W2962739339 @default.
• W3100152912 cites W2962783425 @default.
• W3100152912 cites W2962884963 @default.
• W3100152912 cites W2963106996 @default.
• W3100152912 cites W2963341956 @default.
• W3100152912 cites W2963477884 @default.
• W3100152912 cites W2963559848 @default.
• W3100152912 cites W2963560049 @default.
• W3100152912 cites W2963588172 @default.
• W3100152912 cites W2963876099 @default.
• W3100152912 cites W2964001908 @default.
• W3100152912 cites W2964189064 @default.
• W3100152912 cites W2964210218 @default.
• W3100152912 cites W2964352358 @default.
• W3100152912 cites W2964588180 @default.
• W3100152912 cites W2971146255 @default.
• W3100152912 cites W3003289092 @default.
• W3100152912 cites W3034856281 @default.
• W3100152912 cites W3038345636 @default.
• W3100152912 cites W3043271475 @default.
• W3100152912 cites W3088966581 @default.
• W3100152912 cites W3091322135 @default.
• W3100152912 cites W3100380967 @default.
• W3100152912 cites W3102767808 @default.
• W3100152912 cites W3102854726 @default.
• W3100152912 cites W3104215796 @default.
• W3100152912 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.310" @default.
• W3100152912 hasPublicationYear "2020" @default.
• W3100152912 type Work @default.
• W3100152912 sameAs 3100152912 @default.
• W3100152912 citedByCount "17" @default.
• W3100152912 countsByYear W31001529122020 @default.
• W3100152912 countsByYear W31001529122021 @default.
• W3100152912 countsByYear W31001529122022 @default.
• W3100152912 countsByYear W31001529122023 @default.
• W3100152912 crossrefType "proceedings-article" @default.
• W3100152912 hasAuthorship W3100152912A5012014905 @default.
• W3100152912 hasAuthorship W3100152912A5049682051 @default.
• W3100152912 hasAuthorship W3100152912A5058504936 @default.
• W3100152912 hasAuthorship W3100152912A5060427576 @default.
• W3100152912 hasAuthorship W3100152912A5071250011 @default.
• W3100152912 hasBestOaLocation W31001529121 @default.
• W3100152912 hasConcept C119857082 @default.
• W3100152912 hasConcept C13280743 @default.
• W3100152912 hasConcept C136764020 @default.
• W3100152912 hasConcept C138885662 @default.
• W3100152912 hasConcept C154945302 @default.
• W3100152912 hasConcept C162324750 @default.
• W3100152912 hasConcept C173853756 @default.
• W3100152912 hasConcept C185798385 @default.
• W3100152912 hasConcept C187736073 @default.
• W3100152912 hasConcept C195324797 @default.
• W3100152912 hasConcept C205649164 @default.
• W3100152912 hasConcept C2776187449 @default.
• W3100152912 hasConcept C2776999362 @default.
• W3100152912 hasConcept C2779439875 @default.
• W3100152912 hasConcept C2780451532 @default.
• W3100152912 hasConcept C41008148 @default.
• W3100152912 hasConcept C41895202 @default.
• W3100152912 hasConcept C7149132 @default.
• W3100152912 hasConceptScore W3100152912C119857082 @default.
• W3100152912 hasConceptScore W3100152912C13280743 @default.
• W3100152912 hasConceptScore W3100152912C136764020 @default.
• W3100152912 hasConceptScore W3100152912C138885662 @default.
• W3100152912 hasConceptScore W3100152912C154945302 @default.
• W3100152912 hasConceptScore W3100152912C162324750 @default.
• W3100152912 hasConceptScore W3100152912C173853756 @default.

• next