Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105626768> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3105626768 abstract "Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods." @default.
- W3105626768 created "2020-11-23" @default.
- W3105626768 creator A5037949684 @default.
- W3105626768 creator A5043069455 @default.
- W3105626768 creator A5048381807 @default.
- W3105626768 creator A5067981703 @default.
- W3105626768 creator A5069862455 @default.
- W3105626768 date "2020-01-01" @default.
- W3105626768 modified "2023-10-16" @default.
- W3105626768 title "Learning Adaptive Segmentation Policy for Simultaneous Translation" @default.
- W3105626768 cites W2101105183 @default.
- W3105626768 cites W2121457870 @default.
- W3105626768 cites W2251955814 @default.
- W3105626768 cites W2419292002 @default.
- W3105626768 cites W2529548870 @default.
- W3105626768 cites W2890698823 @default.
- W3105626768 cites W2896234185 @default.
- W3105626768 cites W2938830017 @default.
- W3105626768 cites W2951642234 @default.
- W3105626768 cites W2962784628 @default.
- W3105626768 cites W2963341956 @default.
- W3105626768 cites W2963403868 @default.
- W3105626768 cites W2964078338 @default.
- W3105626768 cites W2970074184 @default.
- W3105626768 cites W2995428172 @default.
- W3105626768 cites W3035348852 @default.
- W3105626768 cites W808583520 @default.
- W3105626768 doi "https://doi.org/10.18653/v1/2020.emnlp-main.178" @default.
- W3105626768 hasPublicationYear "2020" @default.
- W3105626768 type Work @default.
- W3105626768 sameAs 3105626768 @default.
- W3105626768 citedByCount "14" @default.
- W3105626768 countsByYear W31056267682021 @default.
- W3105626768 countsByYear W31056267682023 @default.
- W3105626768 crossrefType "proceedings-article" @default.
- W3105626768 hasAuthorship W3105626768A5037949684 @default.
- W3105626768 hasAuthorship W3105626768A5043069455 @default.
- W3105626768 hasAuthorship W3105626768A5048381807 @default.
- W3105626768 hasAuthorship W3105626768A5067981703 @default.
- W3105626768 hasAuthorship W3105626768A5069862455 @default.
- W3105626768 hasBestOaLocation W31056267681 @default.
- W3105626768 hasConcept C104317684 @default.
- W3105626768 hasConcept C105580179 @default.
- W3105626768 hasConcept C122783720 @default.
- W3105626768 hasConcept C149364088 @default.
- W3105626768 hasConcept C154945302 @default.
- W3105626768 hasConcept C185592680 @default.
- W3105626768 hasConcept C199360897 @default.
- W3105626768 hasConcept C204321447 @default.
- W3105626768 hasConcept C2776436953 @default.
- W3105626768 hasConcept C28490314 @default.
- W3105626768 hasConcept C41008148 @default.
- W3105626768 hasConcept C55493867 @default.
- W3105626768 hasConcept C76155785 @default.
- W3105626768 hasConcept C82876162 @default.
- W3105626768 hasConcept C89600930 @default.
- W3105626768 hasConceptScore W3105626768C104317684 @default.
- W3105626768 hasConceptScore W3105626768C105580179 @default.
- W3105626768 hasConceptScore W3105626768C122783720 @default.
- W3105626768 hasConceptScore W3105626768C149364088 @default.
- W3105626768 hasConceptScore W3105626768C154945302 @default.
- W3105626768 hasConceptScore W3105626768C185592680 @default.
- W3105626768 hasConceptScore W3105626768C199360897 @default.
- W3105626768 hasConceptScore W3105626768C204321447 @default.
- W3105626768 hasConceptScore W3105626768C2776436953 @default.
- W3105626768 hasConceptScore W3105626768C28490314 @default.
- W3105626768 hasConceptScore W3105626768C41008148 @default.
- W3105626768 hasConceptScore W3105626768C55493867 @default.
- W3105626768 hasConceptScore W3105626768C76155785 @default.
- W3105626768 hasConceptScore W3105626768C82876162 @default.
- W3105626768 hasConceptScore W3105626768C89600930 @default.
- W3105626768 hasLocation W31056267681 @default.
- W3105626768 hasOpenAccess W3105626768 @default.
- W3105626768 hasPrimaryLocation W31056267681 @default.
- W3105626768 hasRelatedWork W10287945 @default.
- W3105626768 hasRelatedWork W10667231 @default.
- W3105626768 hasRelatedWork W11012074 @default.
- W3105626768 hasRelatedWork W12732426 @default.
- W3105626768 hasRelatedWork W14712889 @default.
- W3105626768 hasRelatedWork W1619002 @default.
- W3105626768 hasRelatedWork W2864082 @default.
- W3105626768 hasRelatedWork W3164750 @default.
- W3105626768 hasRelatedWork W4629839 @default.
- W3105626768 hasRelatedWork W5952272 @default.
- W3105626768 isParatext "false" @default.
- W3105626768 isRetracted "false" @default.
- W3105626768 magId "3105626768" @default.
- W3105626768 workType "article" @default.