Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887005286> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2887005286 abstract "Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping from source sentences to target sentences. But with this ability, new challenges also arise. An example is the translation of partial sentences in low-latency speech translation. Since the model has only seen complete sentences in training, it will always try to generate a complete sentence, though the input may only be a partial sentence. We show that NMT systems can be adapted to scenarios where no task-specific training data is available. Furthermore, this is possible without losing performance on the original training data. We achieve this by creating artificial data and by using multi-task learning. After adaptation, we are able to reduce the number of corrections displayed during incremental output construction by 45%, without a decrease in translation quality." @default.
- W2887005286 created "2018-08-22" @default.
- W2887005286 creator A5004365148 @default.
- W2887005286 creator A5007526409 @default.
- W2887005286 creator A5024736091 @default.
- W2887005286 creator A5025976094 @default.
- W2887005286 creator A5046084081 @default.
- W2887005286 date "2018-09-02" @default.
- W2887005286 modified "2023-09-23" @default.
- W2887005286 title "Low-Latency Neural Speech Translation" @default.
- W2887005286 doi "https://doi.org/10.21437/interspeech.2018-1055" @default.
- W2887005286 hasPublicationYear "2018" @default.
- W2887005286 type Work @default.
- W2887005286 sameAs 2887005286 @default.
- W2887005286 citedByCount "27" @default.
- W2887005286 countsByYear W28870052862018 @default.
- W2887005286 countsByYear W28870052862019 @default.
- W2887005286 countsByYear W28870052862020 @default.
- W2887005286 countsByYear W28870052862021 @default.
- W2887005286 countsByYear W28870052862023 @default.
- W2887005286 crossrefType "proceedings-article" @default.
- W2887005286 hasAuthorship W2887005286A5004365148 @default.
- W2887005286 hasAuthorship W2887005286A5007526409 @default.
- W2887005286 hasAuthorship W2887005286A5024736091 @default.
- W2887005286 hasAuthorship W2887005286A5025976094 @default.
- W2887005286 hasAuthorship W2887005286A5046084081 @default.
- W2887005286 hasBestOaLocation W28870052862 @default.
- W2887005286 hasConcept C104317684 @default.
- W2887005286 hasConcept C105580179 @default.
- W2887005286 hasConcept C108583219 @default.
- W2887005286 hasConcept C120665830 @default.
- W2887005286 hasConcept C121332964 @default.
- W2887005286 hasConcept C139807058 @default.
- W2887005286 hasConcept C149364088 @default.
- W2887005286 hasConcept C154945302 @default.
- W2887005286 hasConcept C162324750 @default.
- W2887005286 hasConcept C185592680 @default.
- W2887005286 hasConcept C187736073 @default.
- W2887005286 hasConcept C203005215 @default.
- W2887005286 hasConcept C204321447 @default.
- W2887005286 hasConcept C2777530160 @default.
- W2887005286 hasConcept C2780366754 @default.
- W2887005286 hasConcept C2780451532 @default.
- W2887005286 hasConcept C28490314 @default.
- W2887005286 hasConcept C41008148 @default.
- W2887005286 hasConcept C50644808 @default.
- W2887005286 hasConcept C55493867 @default.
- W2887005286 hasConcept C76155785 @default.
- W2887005286 hasConcept C82876162 @default.
- W2887005286 hasConceptScore W2887005286C104317684 @default.
- W2887005286 hasConceptScore W2887005286C105580179 @default.
- W2887005286 hasConceptScore W2887005286C108583219 @default.
- W2887005286 hasConceptScore W2887005286C120665830 @default.
- W2887005286 hasConceptScore W2887005286C121332964 @default.
- W2887005286 hasConceptScore W2887005286C139807058 @default.
- W2887005286 hasConceptScore W2887005286C149364088 @default.
- W2887005286 hasConceptScore W2887005286C154945302 @default.
- W2887005286 hasConceptScore W2887005286C162324750 @default.
- W2887005286 hasConceptScore W2887005286C185592680 @default.
- W2887005286 hasConceptScore W2887005286C187736073 @default.
- W2887005286 hasConceptScore W2887005286C203005215 @default.
- W2887005286 hasConceptScore W2887005286C204321447 @default.
- W2887005286 hasConceptScore W2887005286C2777530160 @default.
- W2887005286 hasConceptScore W2887005286C2780366754 @default.
- W2887005286 hasConceptScore W2887005286C2780451532 @default.
- W2887005286 hasConceptScore W2887005286C28490314 @default.
- W2887005286 hasConceptScore W2887005286C41008148 @default.
- W2887005286 hasConceptScore W2887005286C50644808 @default.
- W2887005286 hasConceptScore W2887005286C55493867 @default.
- W2887005286 hasConceptScore W2887005286C76155785 @default.
- W2887005286 hasConceptScore W2887005286C82876162 @default.
- W2887005286 hasLocation W28870052861 @default.
- W2887005286 hasLocation W28870052862 @default.
- W2887005286 hasOpenAccess W2887005286 @default.
- W2887005286 hasPrimaryLocation W28870052861 @default.
- W2887005286 hasRelatedWork W2016144213 @default.
- W2887005286 hasRelatedWork W2101456909 @default.
- W2887005286 hasRelatedWork W2134352815 @default.
- W2887005286 hasRelatedWork W2168262690 @default.
- W2887005286 hasRelatedWork W2234508350 @default.
- W2887005286 hasRelatedWork W2885616807 @default.
- W2887005286 hasRelatedWork W2973172486 @default.
- W2887005286 hasRelatedWork W3105962700 @default.
- W2887005286 hasRelatedWork W3156425279 @default.
- W2887005286 hasRelatedWork W83095340 @default.
- W2887005286 isParatext "false" @default.
- W2887005286 isRetracted "false" @default.
- W2887005286 magId "2887005286" @default.
- W2887005286 workType "article" @default.