Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890419630> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2890419630 abstract "In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstrating that BanditSum is able to achieve ROUGE scores that are better than or comparable to the state-of-the-art for extractive summarization, and converges using significantly fewer update steps than competing approaches. In addition, we show empirically that BanditSum performs significantly better than competing approaches when good summary sentences appear late in the source document." @default.
- W2890419630 created "2018-09-27" @default.
- W2890419630 creator A5023300851 @default.
- W2890419630 creator A5050801868 @default.
- W2890419630 creator A5057277609 @default.
- W2890419630 creator A5063215270 @default.
- W2890419630 creator A5073742611 @default.
- W2890419630 date "2018-01-01" @default.
- W2890419630 modified "2023-10-10" @default.
- W2890419630 title "BanditSum: Extractive Summarization as a Contextual Bandit" @default.
- W2890419630 cites W1525595230 @default.
- W2890419630 cites W1544827683 @default.
- W2890419630 cites W1614298861 @default.
- W2890419630 cites W1832693441 @default.
- W2890419630 cites W1924770834 @default.
- W2890419630 cites W1967082914 @default.
- W2890419630 cites W1974339500 @default.
- W2890419630 cites W2054211469 @default.
- W2890419630 cites W2120615054 @default.
- W2890419630 cites W2140476275 @default.
- W2890419630 cites W2154652894 @default.
- W2890419630 cites W2155027007 @default.
- W2890419630 cites W2170213349 @default.
- W2890419630 cites W2250539671 @default.
- W2890419630 cites W2251911042 @default.
- W2890419630 cites W2288604516 @default.
- W2890419630 cites W2307381258 @default.
- W2890419630 cites W2507756961 @default.
- W2890419630 cites W2574535369 @default.
- W2890419630 cites W2606974598 @default.
- W2890419630 cites W2790702239 @default.
- W2890419630 cites W2962762898 @default.
- W2890419630 cites W2962972512 @default.
- W2890419630 cites W2962985882 @default.
- W2890419630 cites W2963084599 @default.
- W2890419630 cites W2963929190 @default.
- W2890419630 cites W2964121744 @default.
- W2890419630 cites W2964144561 @default.
- W2890419630 cites W2964352247 @default.
- W2890419630 cites W303217050 @default.
- W2890419630 doi "https://doi.org/10.18653/v1/d18-1409" @default.
- W2890419630 hasPublicationYear "2018" @default.
- W2890419630 type Work @default.
- W2890419630 sameAs 2890419630 @default.
- W2890419630 citedByCount "120" @default.
- W2890419630 countsByYear W28904196302019 @default.
- W2890419630 countsByYear W28904196302020 @default.
- W2890419630 countsByYear W28904196302021 @default.
- W2890419630 countsByYear W28904196302022 @default.
- W2890419630 countsByYear W28904196302023 @default.
- W2890419630 crossrefType "proceedings-article" @default.
- W2890419630 hasAuthorship W2890419630A5023300851 @default.
- W2890419630 hasAuthorship W2890419630A5050801868 @default.
- W2890419630 hasAuthorship W2890419630A5057277609 @default.
- W2890419630 hasAuthorship W2890419630A5063215270 @default.
- W2890419630 hasAuthorship W2890419630A5073742611 @default.
- W2890419630 hasBestOaLocation W28904196301 @default.
- W2890419630 hasConcept C119857082 @default.
- W2890419630 hasConcept C151730666 @default.
- W2890419630 hasConcept C154945302 @default.
- W2890419630 hasConcept C170858558 @default.
- W2890419630 hasConcept C204321447 @default.
- W2890419630 hasConcept C2778112365 @default.
- W2890419630 hasConcept C2779343474 @default.
- W2890419630 hasConcept C41008148 @default.
- W2890419630 hasConcept C54355233 @default.
- W2890419630 hasConcept C86803240 @default.
- W2890419630 hasConcept C97541855 @default.
- W2890419630 hasConceptScore W2890419630C119857082 @default.
- W2890419630 hasConceptScore W2890419630C151730666 @default.
- W2890419630 hasConceptScore W2890419630C154945302 @default.
- W2890419630 hasConceptScore W2890419630C170858558 @default.
- W2890419630 hasConceptScore W2890419630C204321447 @default.
- W2890419630 hasConceptScore W2890419630C2778112365 @default.
- W2890419630 hasConceptScore W2890419630C2779343474 @default.
- W2890419630 hasConceptScore W2890419630C41008148 @default.
- W2890419630 hasConceptScore W2890419630C54355233 @default.
- W2890419630 hasConceptScore W2890419630C86803240 @default.
- W2890419630 hasConceptScore W2890419630C97541855 @default.
- W2890419630 hasLocation W28904196301 @default.
- W2890419630 hasLocation W28904196302 @default.
- W2890419630 hasLocation W28904196303 @default.
- W2890419630 hasLocation W28904196304 @default.
- W2890419630 hasOpenAccess W2890419630 @default.
- W2890419630 hasPrimaryLocation W28904196301 @default.
- W2890419630 hasRelatedWork W2293457016 @default.
- W2890419630 hasRelatedWork W2747680751 @default.
- W2890419630 hasRelatedWork W2964945503 @default.
- W2890419630 hasRelatedWork W3014410397 @default.
- W2890419630 hasRelatedWork W3022038857 @default.
- W2890419630 hasRelatedWork W3107474891 @default.
- W2890419630 hasRelatedWork W3211051370 @default.
- W2890419630 hasRelatedWork W4313415421 @default.
- W2890419630 hasRelatedWork W4319083788 @default.
- W2890419630 hasRelatedWork W4323363096 @default.
- W2890419630 isParatext "false" @default.
- W2890419630 isRetracted "false" @default.
- W2890419630 magId "2890419630" @default.
- W2890419630 workType "article" @default.