FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970390610> ?p ?o ?g. }

• W2970390610 abstract "While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To solve the mismatch between training and inference as well as modeling label dependencies in a more principled way, we formulate HTC as a Markov decision process and propose to learn a Label Assignment Policy via deep reinforcement learning to determine where to place an object and when to stop the assignment process. The proposed method, HiLAP, explores the hierarchy during both training and inference time in a consistent manner and makes inter-dependent decisions. As a general framework, HiLAP can incorporate different neural encoders as base models for end-to-end training. Experiments on five public datasets and four base models show that HiLAP yields an average improvement of 33.4% in Macro-F1 over flat classifiers and outperforms state-of-the-art HTC methods by a large margin. Data and code can be found at https://github.com/morningmoni/HiLAP." @default.
• W2970390610 created "2019-09-05" @default.
• W2970390610 creator A5009408707 @default.
• W2970390610 creator A5012370787 @default.
• W2970390610 creator A5019539533 @default.
• W2970390610 creator A5053540196 @default.
• W2970390610 date "2019-01-01" @default.
• W2970390610 modified "2023-10-16" @default.
• W2970390610 title "Hierarchical Text Classification with Reinforced Label Assignment" @default.
• W2970390610 cites W1590163898 @default.
• W2970390610 cites W1620204465 @default.
• W2970390610 cites W1643574276 @default.
• W2970390610 cites W1832693441 @default.
• W2970390610 cites W1834987204 @default.
• W2970390610 cites W1841724727 @default.
• W2970390610 cites W1967542092 @default.
• W2970390610 cites W1977224551 @default.
• W2970390610 cites W2014566476 @default.
• W2970390610 cites W2025047573 @default.
• W2970390610 cites W2091961126 @default.
• W2970390610 cites W2105842272 @default.
• W2970390610 cites W2106667958 @default.
• W2970390610 cites W2117225622 @default.
• W2970390610 cites W2127723919 @default.
• W2970390610 cites W2132826100 @default.
• W2970390610 cites W2137165876 @default.
• W2970390610 cites W2137810087 @default.
• W2970390610 cites W2150102617 @default.
• W2970390610 cites W2150766729 @default.
• W2970390610 cites W2157438458 @default.
• W2970390610 cites W2171066191 @default.
• W2970390610 cites W2250539671 @default.
• W2970390610 cites W2265846598 @default.
• W2970390610 cites W2428528690 @default.
• W2970390610 cites W2470673105 @default.
• W2970390610 cites W2520368209 @default.
• W2970390610 cites W2739996966 @default.
• W2970390610 cites W2788667846 @default.
• W2970390610 cites W2803270043 @default.
• W2970390610 cites W2890931111 @default.
• W2970390610 cites W2949541494 @default.
• W2970390610 cites W2963007351 @default.
• W2970390610 cites W2963084599 @default.
• W2970390610 cites W2963173796 @default.
• W2970390610 cites W2963385935 @default.
• W2970390610 cites W2963921497 @default.
• W2970390610 cites W2964308564 @default.
• W2970390610 cites W3158986179 @default.
• W2970390610 cites W756166754 @default.
• W2970390610 doi "https://doi.org/10.18653/v1/d19-1042" @default.
• W2970390610 hasPublicationYear "2019" @default.
• W2970390610 type Work @default.
• W2970390610 sameAs 2970390610 @default.
• W2970390610 citedByCount "46" @default.
• W2970390610 countsByYear W29703906102020 @default.
• W2970390610 countsByYear W29703906102021 @default.
• W2970390610 countsByYear W29703906102022 @default.
• W2970390610 countsByYear W29703906102023 @default.
• W2970390610 crossrefType "proceedings-article" @default.
• W2970390610 hasAuthorship W2970390610A5009408707 @default.
• W2970390610 hasAuthorship W2970390610A5012370787 @default.
• W2970390610 hasAuthorship W2970390610A5019539533 @default.
• W2970390610 hasAuthorship W2970390610A5053540196 @default.
• W2970390610 hasBestOaLocation W29703906101 @default.
• W2970390610 hasConcept C105795698 @default.
• W2970390610 hasConcept C106189395 @default.
• W2970390610 hasConcept C111919701 @default.
• W2970390610 hasConcept C118505674 @default.
• W2970390610 hasConcept C119857082 @default.
• W2970390610 hasConcept C124101348 @default.
• W2970390610 hasConcept C134306372 @default.
• W2970390610 hasConcept C154945302 @default.
• W2970390610 hasConcept C159886148 @default.
• W2970390610 hasConcept C162324750 @default.
• W2970390610 hasConcept C166955791 @default.
• W2970390610 hasConcept C177264268 @default.
• W2970390610 hasConcept C199360897 @default.
• W2970390610 hasConcept C2776214188 @default.
• W2970390610 hasConcept C2776760102 @default.
• W2970390610 hasConcept C31170391 @default.
• W2970390610 hasConcept C33923547 @default.
• W2970390610 hasConcept C34447519 @default.
• W2970390610 hasConcept C41008148 @default.
• W2970390610 hasConcept C42058472 @default.
• W2970390610 hasConcept C50644808 @default.
• W2970390610 hasConcept C774472 @default.
• W2970390610 hasConcept C97541855 @default.
• W2970390610 hasConcept C98045186 @default.
• W2970390610 hasConceptScore W2970390610C105795698 @default.
• W2970390610 hasConceptScore W2970390610C106189395 @default.
• W2970390610 hasConceptScore W2970390610C111919701 @default.
• W2970390610 hasConceptScore W2970390610C118505674 @default.
• W2970390610 hasConceptScore W2970390610C119857082 @default.
• W2970390610 hasConceptScore W2970390610C124101348 @default.
• W2970390610 hasConceptScore W2970390610C134306372 @default.
• W2970390610 hasConceptScore W2970390610C154945302 @default.
• W2970390610 hasConceptScore W2970390610C159886148 @default.
• W2970390610 hasConceptScore W2970390610C162324750 @default.
• W2970390610 hasConceptScore W2970390610C166955791 @default.
• W2970390610 hasConceptScore W2970390610C177264268 @default.

• next