FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2621167245> ?p ?o ?g. }

• W2621167245 abstract "In this paper, we present an investigation on technical details of the byte-level convolutional layer which replaces the conventional linear word projection layer in the neural language model. In particular, we discuss and compare the effective filter configurations, pooling types and the use of bytes instead of characters. We carry out experiments on language packs released by the IARPA Babel project and measure the performance in terms of perplexity and word error rate. Introducing a convolutional layer consistently improves the results on all languages. Also, there is no degradation from using raw bytes instead of proper Unicode characters, even on syllabic alphabets like Amharic. In addition, we report improvements in word error rate from rescoring lattices and evaluate keyword search performance on several languages." @default.
• W2621167245 created "2017-06-09" @default.
• W2621167245 creator A5002810304 @default.
• W2621167245 creator A5015194760 @default.
• W2621167245 creator A5087367411 @default.
• W2621167245 creator A5088968292 @default.
• W2621167245 date "2017-03-01" @default.
• W2621167245 modified "2023-10-10" @default.
• W2621167245 title "Investigations on byte-level convolutional neural networks for language modeling in low resource speech recognition" @default.
• W2621167245 cites W1026270304 @default.
• W2621167245 cites W1899794420 @default.
• W2621167245 cites W1938755728 @default.
• W2621167245 cites W1985258458 @default.
• W2621167245 cites W1992912377 @default.
• W2621167245 cites W2064675550 @default.
• W2621167245 cites W2147800946 @default.
• W2621167245 cites W2259472270 @default.
• W2621167245 cites W2267126114 @default.
• W2621167245 cites W2401869809 @default.
• W2621167245 cites W2402393661 @default.
• W2621167245 cites W2404974730 @default.
• W2621167245 cites W2408093180 @default.
• W2621167245 cites W2408752871 @default.
• W2621167245 cites W2442329935 @default.
• W2621167245 cites W2516310076 @default.
• W2621167245 cites W2962728618 @default.
• W2621167245 cites W2962732637 @default.
• W2621167245 cites W2963012544 @default.
• W2621167245 cites W2963208801 @default.
• W2621167245 doi "https://doi.org/10.1109/icassp.2017.7953256" @default.
• W2621167245 hasPublicationYear "2017" @default.
• W2621167245 type Work @default.
• W2621167245 sameAs 2621167245 @default.
• W2621167245 citedByCount "5" @default.
• W2621167245 countsByYear W26211672452017 @default.
• W2621167245 countsByYear W26211672452018 @default.
• W2621167245 crossrefType "proceedings-article" @default.
• W2621167245 hasAuthorship W2621167245A5002810304 @default.
• W2621167245 hasAuthorship W2621167245A5015194760 @default.
• W2621167245 hasAuthorship W2621167245A5087367411 @default.
• W2621167245 hasAuthorship W2621167245A5088968292 @default.
• W2621167245 hasConcept C100279451 @default.
• W2621167245 hasConcept C137293760 @default.
• W2621167245 hasConcept C138885662 @default.
• W2621167245 hasConcept C154945302 @default.
• W2621167245 hasConcept C178790620 @default.
• W2621167245 hasConcept C185592680 @default.
• W2621167245 hasConcept C199360897 @default.
• W2621167245 hasConcept C204321447 @default.
• W2621167245 hasConcept C2779227376 @default.
• W2621167245 hasConcept C2780900699 @default.
• W2621167245 hasConcept C28490314 @default.
• W2621167245 hasConcept C40969351 @default.
• W2621167245 hasConcept C41008148 @default.
• W2621167245 hasConcept C41895202 @default.
• W2621167245 hasConcept C43364308 @default.
• W2621167245 hasConcept C500551929 @default.
• W2621167245 hasConcept C70437156 @default.
• W2621167245 hasConcept C81363708 @default.
• W2621167245 hasConcept C90805587 @default.
• W2621167245 hasConceptScore W2621167245C100279451 @default.
• W2621167245 hasConceptScore W2621167245C137293760 @default.
• W2621167245 hasConceptScore W2621167245C138885662 @default.
• W2621167245 hasConceptScore W2621167245C154945302 @default.
• W2621167245 hasConceptScore W2621167245C178790620 @default.
• W2621167245 hasConceptScore W2621167245C185592680 @default.
• W2621167245 hasConceptScore W2621167245C199360897 @default.
• W2621167245 hasConceptScore W2621167245C204321447 @default.
• W2621167245 hasConceptScore W2621167245C2779227376 @default.
• W2621167245 hasConceptScore W2621167245C2780900699 @default.
• W2621167245 hasConceptScore W2621167245C28490314 @default.
• W2621167245 hasConceptScore W2621167245C40969351 @default.
• W2621167245 hasConceptScore W2621167245C41008148 @default.
• W2621167245 hasConceptScore W2621167245C41895202 @default.
• W2621167245 hasConceptScore W2621167245C43364308 @default.
• W2621167245 hasConceptScore W2621167245C500551929 @default.
• W2621167245 hasConceptScore W2621167245C70437156 @default.
• W2621167245 hasConceptScore W2621167245C81363708 @default.
• W2621167245 hasConceptScore W2621167245C90805587 @default.
• W2621167245 hasLocation W26211672451 @default.
• W2621167245 hasOpenAccess W2621167245 @default.
• W2621167245 hasPrimaryLocation W26211672451 @default.
• W2621167245 hasRelatedWork W2127099688 @default.
• W2621167245 hasRelatedWork W2399351785 @default.
• W2621167245 hasRelatedWork W2407467516 @default.
• W2621167245 hasRelatedWork W2545177271 @default.
• W2621167245 hasRelatedWork W2762466393 @default.
• W2621167245 hasRelatedWork W2808971413 @default.
• W2621167245 hasRelatedWork W2896411932 @default.
• W2621167245 hasRelatedWork W2912418351 @default.
• W2621167245 hasRelatedWork W2914699162 @default.
• W2621167245 hasRelatedWork W2944691285 @default.
• W2621167245 hasRelatedWork W2952613254 @default.
• W2621167245 hasRelatedWork W2962824709 @default.
• W2621167245 hasRelatedWork W2963070863 @default.
• W2621167245 hasRelatedWork W2963362078 @default.
• W2621167245 hasRelatedWork W3015325583 @default.
• W2621167245 hasRelatedWork W3096509182 @default.
• W2621167245 hasRelatedWork W3155772857 @default.
• W2621167245 hasRelatedWork W3163571828 @default.

• next