Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205514791> ?p ?o ?g. }
- W3205514791 abstract "Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences." @default.
- W3205514791 created "2021-10-25" @default.
- W3205514791 creator A5016697113 @default.
- W3205514791 creator A5022869420 @default.
- W3205514791 creator A5030540307 @default.
- W3205514791 creator A5079394252 @default.
- W3205514791 creator A5080589950 @default.
- W3205514791 creator A5091175785 @default.
- W3205514791 date "2021-10-18" @default.
- W3205514791 modified "2023-09-26" @default.
- W3205514791 title "Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement" @default.
- W3205514791 cites W1498238796 @default.
- W3205514791 cites W2111798208 @default.
- W3205514791 cites W2148708890 @default.
- W3205514791 cites W2156985047 @default.
- W3205514791 cites W2184135559 @default.
- W3205514791 cites W2251994258 @default.
- W3205514791 cites W2419292002 @default.
- W3205514791 cites W2529548870 @default.
- W3205514791 cites W2572474373 @default.
- W3205514791 cites W2741049976 @default.
- W3205514791 cites W2889326796 @default.
- W3205514791 cites W2890698823 @default.
- W3205514791 cites W2933138175 @default.
- W3205514791 cites W2951642234 @default.
- W3205514791 cites W2952992734 @default.
- W3205514791 cites W2963001247 @default.
- W3205514791 cites W2963126845 @default.
- W3205514791 cites W2963250244 @default.
- W3205514791 cites W2963403868 @default.
- W3205514791 cites W2963434219 @default.
- W3205514791 cites W2963532001 @default.
- W3205514791 cites W2963697731 @default.
- W3205514791 cites W2964078338 @default.
- W3205514791 cites W2964247056 @default.
- W3205514791 cites W2970074184 @default.
- W3205514791 cites W2971167892 @default.
- W3205514791 cites W2995404354 @default.
- W3205514791 cites W2995428172 @default.
- W3205514791 cites W2996403597 @default.
- W3205514791 cites W3005389111 @default.
- W3205514791 cites W3034982693 @default.
- W3205514791 cites W3035348852 @default.
- W3205514791 cites W3035463087 @default.
- W3205514791 cites W3037231493 @default.
- W3205514791 cites W3037793211 @default.
- W3205514791 cites W3045875328 @default.
- W3205514791 cites W3093501075 @default.
- W3205514791 cites W3104234009 @default.
- W3205514791 cites W3105626768 @default.
- W3205514791 cites W3105962700 @default.
- W3205514791 cites W3113677452 @default.
- W3205514791 cites W3121114617 @default.
- W3205514791 cites W3174892288 @default.
- W3205514791 cites W2758491225 @default.
- W3205514791 doi "https://doi.org/10.48550/arxiv.2110.09646" @default.
- W3205514791 hasPublicationYear "2021" @default.
- W3205514791 type Work @default.
- W3205514791 sameAs 3205514791 @default.
- W3205514791 citedByCount "0" @default.
- W3205514791 crossrefType "posted-content" @default.
- W3205514791 hasAuthorship W3205514791A5016697113 @default.
- W3205514791 hasAuthorship W3205514791A5022869420 @default.
- W3205514791 hasAuthorship W3205514791A5030540307 @default.
- W3205514791 hasAuthorship W3205514791A5079394252 @default.
- W3205514791 hasAuthorship W3205514791A5080589950 @default.
- W3205514791 hasAuthorship W3205514791A5091175785 @default.
- W3205514791 hasBestOaLocation W32055147911 @default.
- W3205514791 hasConcept C104317684 @default.
- W3205514791 hasConcept C105580179 @default.
- W3205514791 hasConcept C134306372 @default.
- W3205514791 hasConcept C138885662 @default.
- W3205514791 hasConcept C149364088 @default.
- W3205514791 hasConcept C154945302 @default.
- W3205514791 hasConcept C185592680 @default.
- W3205514791 hasConcept C203005215 @default.
- W3205514791 hasConcept C204321447 @default.
- W3205514791 hasConcept C24687705 @default.
- W3205514791 hasConcept C26022165 @default.
- W3205514791 hasConcept C2777530160 @default.
- W3205514791 hasConcept C2779525943 @default.
- W3205514791 hasConcept C28490314 @default.
- W3205514791 hasConcept C33923547 @default.
- W3205514791 hasConcept C41008148 @default.
- W3205514791 hasConcept C41895202 @default.
- W3205514791 hasConcept C55493867 @default.
- W3205514791 hasConcept C622187 @default.
- W3205514791 hasConcept C72169020 @default.
- W3205514791 hasConcept C90805587 @default.
- W3205514791 hasConceptScore W3205514791C104317684 @default.
- W3205514791 hasConceptScore W3205514791C105580179 @default.
- W3205514791 hasConceptScore W3205514791C134306372 @default.
- W3205514791 hasConceptScore W3205514791C138885662 @default.
- W3205514791 hasConceptScore W3205514791C149364088 @default.
- W3205514791 hasConceptScore W3205514791C154945302 @default.
- W3205514791 hasConceptScore W3205514791C185592680 @default.
- W3205514791 hasConceptScore W3205514791C203005215 @default.
- W3205514791 hasConceptScore W3205514791C204321447 @default.
- W3205514791 hasConceptScore W3205514791C24687705 @default.
- W3205514791 hasConceptScore W3205514791C26022165 @default.