FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964330417> ?p ?o ?g. }

• W2964330417 endingPage "476" @default.
• W2964330417 startingPage "462" @default.
• W2964330417 abstract "Sentence simplification aims to improve readability and understandability, based on several operations such as splitting, deletion, and paraphrasing. However, a valid simplified sentence should also be logically entailed by its input sentence. In this work, we first present a strong pointer-copy mechanism based sequence-to-sequence sentence simplification model, and then improve its entailment and paraphrasing capabilities via multi-task learning with related auxiliary tasks of entailment and paraphrase generation. Moreover, we propose a novel ‘multi-level’ layered soft sharing approach where each auxiliary task shares different (higher versus lower) level layers of the sentence simplification model, depending on the task’s semantic versus lexico-syntactic nature. We also introduce a novel multi-armed bandit based training approach that dynamically learns how to effectively switch across tasks during multi-task learning. Experiments on multiple popular datasets demonstrate that our model outperforms competitive simplification systems in SARI and FKGL automatic metrics, and human evaluation. Further, we present several ablation analyses on alternative layer sharing methods, soft versus hard sharing, dynamic multi-armed bandit sampling approaches, and our model’s learned entailment and paraphrasing skills." @default.
• W2964330417 created "2019-07-30" @default.
• W2964330417 creator A5001987532 @default.
• W2964330417 creator A5041591669 @default.
• W2964330417 creator A5075564427 @default.
• W2964330417 date "2018-06-19" @default.
• W2964330417 modified "2023-09-27" @default.
• W2964330417 title "Dynamic Multi-Level Multi-Task Learning for Sentence Simplification" @default.
• W2964330417 cites W1507711477 @default.
• W2964330417 cites W1536680647 @default.
• W2964330417 cites W1544285860 @default.
• W2964330417 cites W1568589650 @default.
• W2964330417 cites W1746111881 @default.
• W2964330417 cites W1840435438 @default.
• W2964330417 cites W1847917847 @default.
• W2964330417 cites W1849277567 @default.
• W2964330417 cites W1964157370 @default.
• W2964330417 cites W1995945562 @default.
• W2964330417 cites W2016522586 @default.
• W2964330417 cites W2042262613 @default.
• W2964330417 cites W2049934117 @default.
• W2964330417 cites W2063490579 @default.
• W2964330417 cites W2077902449 @default.
• W2964330417 cites W2081388731 @default.
• W2964330417 cites W2099092905 @default.
• W2964330417 cites W2101105183 @default.
• W2964330417 cites W2107130271 @default.
• W2964330417 cites W2107726111 @default.
• W2964330417 cites W2108373063 @default.
• W2964330417 cites W2108738385 @default.
• W2964330417 cites W2109802560 @default.
• W2964330417 cites W2109881807 @default.
• W2964330417 cites W2112282043 @default.
• W2964330417 cites W2112644606 @default.
• W2964330417 cites W2115094368 @default.
• W2964330417 cites W2117130368 @default.
• W2964330417 cites W2119954850 @default.
• W2964330417 cites W2124807415 @default.
• W2964330417 cites W2131726681 @default.
• W2964330417 cites W2133182690 @default.
• W2964330417 cites W2145882814 @default.
• W2964330417 cites W2154652894 @default.
• W2964330417 cites W2156422881 @default.
• W2964330417 cites W2168405694 @default.
• W2964330417 cites W2173779128 @default.
• W2964330417 cites W2250225488 @default.
• W2964330417 cites W2250307601 @default.
• W2964330417 cites W2250365808 @default.
• W2964330417 cites W2250531756 @default.
• W2964330417 cites W2250958747 @default.
• W2964330417 cites W2251044566 @default.
• W2964330417 cites W2251200196 @default.
• W2964330417 cites W2251334348 @default.
• W2964330417 cites W2251831371 @default.
• W2964330417 cites W2251919380 @default.
• W2964330417 cites W2251933807 @default.
• W2964330417 cites W22627370 @default.
• W2964330417 cites W2296307963 @default.
• W2964330417 cites W2401830275 @default.
• W2964330417 cites W2413794162 @default.
• W2964330417 cites W2534253848 @default.
• W2964330417 cites W2550821151 @default.
• W2964330417 cites W2556468274 @default.
• W2964330417 cites W2593765977 @default.
• W2964330417 cites W2605243085 @default.
• W2964330417 cites W2606974598 @default.
• W2964330417 cites W2617039999 @default.
• W2964330417 cites W2626792426 @default.
• W2964330417 cites W2757675222 @default.
• W2964330417 cites W2770626128 @default.
• W2964330417 cites W2914746235 @default.
• W2964330417 cites W2963639957 @default.
• W2964330417 cites W2963842982 @default.
• W2964330417 cites W2963846996 @default.
• W2964330417 cites W2963899155 @default.
• W2964330417 cites W2964065937 @default.
• W2964330417 cites W2964121744 @default.
• W2964330417 cites W2964285114 @default.
• W2964330417 cites W2964308564 @default.
• W2964330417 cites W2964327384 @default.
• W2964330417 cites W45452291 @default.
• W2964330417 cites W67948907 @default.
• W2964330417 cites W2525127255 @default.
• W2964330417 hasPublicationYear "2018" @default.
• W2964330417 type Work @default.
• W2964330417 sameAs 2964330417 @default.
• W2964330417 citedByCount "35" @default.
• W2964330417 countsByYear W29643304172018 @default.
• W2964330417 countsByYear W29643304172019 @default.
• W2964330417 countsByYear W29643304172020 @default.
• W2964330417 countsByYear W29643304172021 @default.
• W2964330417 crossrefType "proceedings-article" @default.
• W2964330417 hasAuthorship W2964330417A5001987532 @default.
• W2964330417 hasAuthorship W2964330417A5041591669 @default.
• W2964330417 hasAuthorship W2964330417A5075564427 @default.
• W2964330417 hasConcept C134752490 @default.
• W2964330417 hasConcept C150202949 @default.
• W2964330417 hasConcept C154945302 @default.

• next