Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913502658> ?p ?o ?g. }
- W2913502658 endingPage "110" @default.
- W2913502658 startingPage "101" @default.
- W2913502658 abstract "Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common languages, such as English. Conversely, research in minority languages, including sign languages, is hampered by the severe lack of data. This has led to work on transfer learning methods, whereby a model developed for one language is reused as the starting point for a model on a second language, which is less resourced. In this paper, we examine two transfer learning techniques of fine-tuning and layer substitution for language modelling of British Sign Language. Our results show improvement in perplexity when using transfer learning with standard stacked LSTM models, trained initially using a large corpus for standard English from the Penn Treebank corpus." @default.
- W2913502658 created "2019-02-21" @default.
- W2913502658 creator A5028774283 @default.
- W2913502658 creator A5042808088 @default.
- W2913502658 creator A5084819987 @default.
- W2913502658 date "2018-08-01" @default.
- W2913502658 modified "2023-09-26" @default.
- W2913502658 title "Transfer Learning for British Sign Language Modelling" @default.
- W2913502658 cites W1490721004 @default.
- W2913502658 cites W1511991230 @default.
- W2913502658 cites W1512014753 @default.
- W2913502658 cites W1631260214 @default.
- W2913502658 cites W179875071 @default.
- W2913502658 cites W1920292565 @default.
- W2913502658 cites W1922655562 @default.
- W2913502658 cites W1931184598 @default.
- W2913502658 cites W1942925989 @default.
- W2913502658 cites W2047687344 @default.
- W2913502658 cites W2076094076 @default.
- W2913502658 cites W2077566853 @default.
- W2913502658 cites W2090291326 @default.
- W2913502658 cites W2091636093 @default.
- W2913502658 cites W2100506586 @default.
- W2913502658 cites W2129574239 @default.
- W2913502658 cites W2132339004 @default.
- W2913502658 cites W2149933564 @default.
- W2913502658 cites W2158195707 @default.
- W2913502658 cites W2250689755 @default.
- W2913502658 cites W2252218224 @default.
- W2913502658 cites W2291817131 @default.
- W2913502658 cites W2513079830 @default.
- W2913502658 cites W2516310076 @default.
- W2913502658 cites W2538552469 @default.
- W2913502658 cites W2550893117 @default.
- W2913502658 cites W2585754816 @default.
- W2913502658 cites W2588820066 @default.
- W2913502658 cites W2743945814 @default.
- W2913502658 cites W2747236259 @default.
- W2913502658 cites W2759336060 @default.
- W2913502658 cites W2792376130 @default.
- W2913502658 cites W2963993537 @default.
- W2913502658 cites W46193368 @default.
- W2913502658 cites W92271087 @default.
- W2913502658 hasPublicationYear "2018" @default.
- W2913502658 type Work @default.
- W2913502658 sameAs 2913502658 @default.
- W2913502658 citedByCount "3" @default.
- W2913502658 countsByYear W29135026582020 @default.
- W2913502658 countsByYear W29135026582021 @default.
- W2913502658 crossrefType "proceedings-article" @default.
- W2913502658 hasAuthorship W2913502658A5028774283 @default.
- W2913502658 hasAuthorship W2913502658A5042808088 @default.
- W2913502658 hasAuthorship W2913502658A5084819987 @default.
- W2913502658 hasConcept C100279451 @default.
- W2913502658 hasConcept C108583219 @default.
- W2913502658 hasConcept C137293760 @default.
- W2913502658 hasConcept C138885662 @default.
- W2913502658 hasConcept C150899416 @default.
- W2913502658 hasConcept C154945302 @default.
- W2913502658 hasConcept C204321447 @default.
- W2913502658 hasConcept C206134035 @default.
- W2913502658 hasConcept C2524010 @default.
- W2913502658 hasConcept C2776321320 @default.
- W2913502658 hasConcept C2776737515 @default.
- W2913502658 hasConcept C28719098 @default.
- W2913502658 hasConcept C33923547 @default.
- W2913502658 hasConcept C41008148 @default.
- W2913502658 hasConcept C41895202 @default.
- W2913502658 hasConcept C522192633 @default.
- W2913502658 hasConceptScore W2913502658C100279451 @default.
- W2913502658 hasConceptScore W2913502658C108583219 @default.
- W2913502658 hasConceptScore W2913502658C137293760 @default.
- W2913502658 hasConceptScore W2913502658C138885662 @default.
- W2913502658 hasConceptScore W2913502658C150899416 @default.
- W2913502658 hasConceptScore W2913502658C154945302 @default.
- W2913502658 hasConceptScore W2913502658C204321447 @default.
- W2913502658 hasConceptScore W2913502658C206134035 @default.
- W2913502658 hasConceptScore W2913502658C2524010 @default.
- W2913502658 hasConceptScore W2913502658C2776321320 @default.
- W2913502658 hasConceptScore W2913502658C2776737515 @default.
- W2913502658 hasConceptScore W2913502658C28719098 @default.
- W2913502658 hasConceptScore W2913502658C33923547 @default.
- W2913502658 hasConceptScore W2913502658C41008148 @default.
- W2913502658 hasConceptScore W2913502658C41895202 @default.
- W2913502658 hasConceptScore W2913502658C522192633 @default.
- W2913502658 hasLocation W29135026581 @default.
- W2913502658 hasOpenAccess W2913502658 @default.
- W2913502658 hasPrimaryLocation W29135026581 @default.
- W2913502658 hasRelatedWork W1492642777 @default.
- W2913502658 hasRelatedWork W1520886244 @default.
- W2913502658 hasRelatedWork W1534064252 @default.
- W2913502658 hasRelatedWork W1663068290 @default.
- W2913502658 hasRelatedWork W2010022641 @default.
- W2913502658 hasRelatedWork W2024958244 @default.
- W2913502658 hasRelatedWork W2033425036 @default.
- W2913502658 hasRelatedWork W2101870992 @default.
- W2913502658 hasRelatedWork W2151447942 @default.
- W2913502658 hasRelatedWork W2164724734 @default.