Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098339586> ?p ?o ?g. }
- W3098339586 abstract "We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task." @default.
- W3098339586 created "2020-11-23" @default.
- W3098339586 creator A5002700508 @default.
- W3098339586 creator A5031185465 @default.
- W3098339586 creator A5073742611 @default.
- W3098339586 creator A5089182977 @default.
- W3098339586 creator A5089919672 @default.
- W3098339586 date "2020-01-01" @default.
- W3098339586 modified "2023-10-14" @default.
- W3098339586 title "Recursive Top-Down Production for Sentence Generation with Latent Trees" @default.
- W3098339586 cites W1840435438 @default.
- W3098339586 cites W1991133427 @default.
- W3098339586 cites W2032005922 @default.
- W3098339586 cites W2047706513 @default.
- W3098339586 cites W2064675550 @default.
- W3098339586 cites W2077574412 @default.
- W3098339586 cites W2123094878 @default.
- W3098339586 cites W2127141656 @default.
- W3098339586 cites W2132827946 @default.
- W3098339586 cites W2144916786 @default.
- W3098339586 cites W2149830985 @default.
- W3098339586 cites W2154292407 @default.
- W3098339586 cites W2157762871 @default.
- W3098339586 cites W2227882979 @default.
- W3098339586 cites W2251939518 @default.
- W3098339586 cites W2510842514 @default.
- W3098339586 cites W2602076750 @default.
- W3098339586 cites W2751262944 @default.
- W3098339586 cites W2885163090 @default.
- W3098339586 cites W2890908793 @default.
- W3098339586 cites W2912937082 @default.
- W3098339586 cites W2920538220 @default.
- W3098339586 cites W2932637973 @default.
- W3098339586 cites W2945686429 @default.
- W3098339586 cites W2949399644 @default.
- W3098339586 cites W2962968135 @default.
- W3098339586 cites W2963073938 @default.
- W3098339586 cites W2963212250 @default.
- W3098339586 cites W2963267799 @default.
- W3098339586 cites W2963403868 @default.
- W3098339586 cites W2963411763 @default.
- W3098339586 cites W2963661253 @default.
- W3098339586 cites W2963754491 @default.
- W3098339586 cites W2964199361 @default.
- W3098339586 cites W2964289395 @default.
- W3098339586 cites W2970060558 @default.
- W3098339586 cites W2970597249 @default.
- W3098339586 cites W2971079754 @default.
- W3098339586 cites W2985694911 @default.
- W3098339586 cites W2996843693 @default.
- W3098339586 cites W3014415613 @default.
- W3098339586 cites W3034552719 @default.
- W3098339586 cites W3145738572 @default.
- W3098339586 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.208" @default.
- W3098339586 hasPublicationYear "2020" @default.
- W3098339586 type Work @default.
- W3098339586 sameAs 3098339586 @default.
- W3098339586 citedByCount "1" @default.
- W3098339586 countsByYear W30983395862021 @default.
- W3098339586 crossrefType "proceedings-article" @default.
- W3098339586 hasAuthorship W3098339586A5002700508 @default.
- W3098339586 hasAuthorship W3098339586A5031185465 @default.
- W3098339586 hasAuthorship W3098339586A5073742611 @default.
- W3098339586 hasAuthorship W3098339586A5089182977 @default.
- W3098339586 hasAuthorship W3098339586A5089919672 @default.
- W3098339586 hasBestOaLocation W30983395861 @default.
- W3098339586 hasConcept C113174947 @default.
- W3098339586 hasConcept C11413529 @default.
- W3098339586 hasConcept C134306372 @default.
- W3098339586 hasConcept C151730666 @default.
- W3098339586 hasConcept C154945302 @default.
- W3098339586 hasConcept C163797641 @default.
- W3098339586 hasConcept C197855036 @default.
- W3098339586 hasConcept C204321447 @default.
- W3098339586 hasConcept C2777530160 @default.
- W3098339586 hasConcept C2779343474 @default.
- W3098339586 hasConcept C33923547 @default.
- W3098339586 hasConcept C41008148 @default.
- W3098339586 hasConcept C53893814 @default.
- W3098339586 hasConcept C80444323 @default.
- W3098339586 hasConcept C86803240 @default.
- W3098339586 hasConceptScore W3098339586C113174947 @default.
- W3098339586 hasConceptScore W3098339586C11413529 @default.
- W3098339586 hasConceptScore W3098339586C134306372 @default.
- W3098339586 hasConceptScore W3098339586C151730666 @default.
- W3098339586 hasConceptScore W3098339586C154945302 @default.
- W3098339586 hasConceptScore W3098339586C163797641 @default.
- W3098339586 hasConceptScore W3098339586C197855036 @default.
- W3098339586 hasConceptScore W3098339586C204321447 @default.
- W3098339586 hasConceptScore W3098339586C2777530160 @default.
- W3098339586 hasConceptScore W3098339586C2779343474 @default.
- W3098339586 hasConceptScore W3098339586C33923547 @default.
- W3098339586 hasConceptScore W3098339586C41008148 @default.
- W3098339586 hasConceptScore W3098339586C53893814 @default.
- W3098339586 hasConceptScore W3098339586C80444323 @default.
- W3098339586 hasConceptScore W3098339586C86803240 @default.
- W3098339586 hasLocation W30983395861 @default.
- W3098339586 hasLocation W30983395862 @default.
- W3098339586 hasOpenAccess W3098339586 @default.
- W3098339586 hasPrimaryLocation W30983395861 @default.