Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902006035> ?p ?o ?g. }
- W2902006035 abstract "This paper describes the Neural Machine Translation (NMT) system of TencentFmRD for Chinese↔English news translation tasks of WMT 2018. Our systems are neural machine translation systems trained with our original system TenTrans. TenTrans is an improved NMT system based on Transformer self-attention mechanism. In addition to the basic settings of Transformer training, TenTrans uses multi-model fusion techniques, multiple features reranking, different segmentation models and joint learning. Finally, we adopt some data selection strategies to fine-tune the trained system and achieve a stable performance improvement. Our Chinese→English system achieved the second best BLEU scores and fourth best cased BLEU scores among all WMT18 submitted systems." @default.
- W2902006035 created "2018-12-11" @default.
- W2902006035 creator A5009739992 @default.
- W2902006035 creator A5034745329 @default.
- W2902006035 creator A5088311174 @default.
- W2902006035 date "2018-01-01" @default.
- W2902006035 modified "2023-09-24" @default.
- W2902006035 title "TencentFmRD Neural Machine Translation for WMT18" @default.
- W2902006035 cites W1591801644 @default.
- W2902006035 cites W1815076433 @default.
- W2902006035 cites W1916559533 @default.
- W2902006035 cites W1940872118 @default.
- W2902006035 cites W2035020702 @default.
- W2902006035 cites W2095705004 @default.
- W2902006035 cites W2101105183 @default.
- W2902006035 cites W2113104171 @default.
- W2902006035 cites W2124807415 @default.
- W2902006035 cites W2130942839 @default.
- W2902006035 cites W2134800885 @default.
- W2902006035 cites W2146574666 @default.
- W2902006035 cites W2148708890 @default.
- W2902006035 cites W2157331557 @default.
- W2902006035 cites W2168231600 @default.
- W2902006035 cites W2183341477 @default.
- W2902006035 cites W2194775991 @default.
- W2902006035 cites W2296283641 @default.
- W2902006035 cites W2740433069 @default.
- W2902006035 cites W2903012348 @default.
- W2902006035 cites W2962784628 @default.
- W2902006035 cites W2963109507 @default.
- W2902006035 cites W2963216553 @default.
- W2902006035 cites W2963324947 @default.
- W2902006035 cites W2963403868 @default.
- W2902006035 cites W2963551569 @default.
- W2902006035 cites W2963841178 @default.
- W2902006035 cites W2964121744 @default.
- W2902006035 cites W2964308564 @default.
- W2902006035 doi "https://doi.org/10.18653/v1/w18-6413" @default.
- W2902006035 hasPublicationYear "2018" @default.
- W2902006035 type Work @default.
- W2902006035 sameAs 2902006035 @default.
- W2902006035 citedByCount "2" @default.
- W2902006035 countsByYear W29020060352018 @default.
- W2902006035 countsByYear W29020060352019 @default.
- W2902006035 crossrefType "proceedings-article" @default.
- W2902006035 hasAuthorship W2902006035A5009739992 @default.
- W2902006035 hasAuthorship W2902006035A5034745329 @default.
- W2902006035 hasAuthorship W2902006035A5088311174 @default.
- W2902006035 hasBestOaLocation W29020060351 @default.
- W2902006035 hasConcept C119599485 @default.
- W2902006035 hasConcept C119857082 @default.
- W2902006035 hasConcept C127413603 @default.
- W2902006035 hasConcept C154945302 @default.
- W2902006035 hasConcept C165801399 @default.
- W2902006035 hasConcept C203005215 @default.
- W2902006035 hasConcept C204321447 @default.
- W2902006035 hasConcept C28490314 @default.
- W2902006035 hasConcept C2986258472 @default.
- W2902006035 hasConcept C41008148 @default.
- W2902006035 hasConcept C51632099 @default.
- W2902006035 hasConcept C622187 @default.
- W2902006035 hasConcept C66322947 @default.
- W2902006035 hasConcept C89600930 @default.
- W2902006035 hasConceptScore W2902006035C119599485 @default.
- W2902006035 hasConceptScore W2902006035C119857082 @default.
- W2902006035 hasConceptScore W2902006035C127413603 @default.
- W2902006035 hasConceptScore W2902006035C154945302 @default.
- W2902006035 hasConceptScore W2902006035C165801399 @default.
- W2902006035 hasConceptScore W2902006035C203005215 @default.
- W2902006035 hasConceptScore W2902006035C204321447 @default.
- W2902006035 hasConceptScore W2902006035C28490314 @default.
- W2902006035 hasConceptScore W2902006035C2986258472 @default.
- W2902006035 hasConceptScore W2902006035C41008148 @default.
- W2902006035 hasConceptScore W2902006035C51632099 @default.
- W2902006035 hasConceptScore W2902006035C622187 @default.
- W2902006035 hasConceptScore W2902006035C66322947 @default.
- W2902006035 hasConceptScore W2902006035C89600930 @default.
- W2902006035 hasLocation W29020060351 @default.
- W2902006035 hasOpenAccess W2902006035 @default.
- W2902006035 hasPrimaryLocation W29020060351 @default.
- W2902006035 hasRelatedWork W2284660317 @default.
- W2902006035 hasRelatedWork W2400065810 @default.
- W2902006035 hasRelatedWork W2757413836 @default.
- W2902006035 hasRelatedWork W2902292292 @default.
- W2902006035 hasRelatedWork W2902367045 @default.
- W2902006035 hasRelatedWork W2902608666 @default.
- W2902006035 hasRelatedWork W2902713373 @default.
- W2902006035 hasRelatedWork W2903399267 @default.
- W2902006035 hasRelatedWork W2903810591 @default.
- W2902006035 hasRelatedWork W2948003005 @default.
- W2902006035 hasRelatedWork W2967985939 @default.
- W2902006035 hasRelatedWork W2970169061 @default.
- W2902006035 hasRelatedWork W2970798168 @default.
- W2902006035 hasRelatedWork W2988335601 @default.
- W2902006035 hasRelatedWork W3118643801 @default.
- W2902006035 hasRelatedWork W3119071063 @default.
- W2902006035 hasRelatedWork W3121049435 @default.
- W2902006035 hasRelatedWork W3136277702 @default.
- W2902006035 hasRelatedWork W3170253133 @default.
- W2902006035 hasRelatedWork W3120459995 @default.