FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3082714809> ?p ?o ?g. }

• W3082714809 endingPage "104" @default.
• W3082714809 startingPage "91" @default.
• W3082714809 abstract "Quality estimation (QE), a task of evaluating the quality of translation automatically without human-translated reference, is one of the important challenges for machine translation (MT). As the QE methods, BLEU score for round-trip translation (RTT) had been considered. However, it was found to be a poor predictor of translation quality since BLEU was not an adequate metric to detect semantic similarity between input and RTT. Recently, the pre-trained language models have made breakthroughs in many NLP tasks by providing semantically meaningful word and sentence embeddings. In this paper, we employ the semantic embeddings to RTT-based QE metric. Our method achieves the highest correlations with human judgments compared to WMT 2019 quality estimation metric task submissions. Additionally, we observe that with semantic-level metrics, RTT-based QE is robust to the choice of a backward translation system and shows consistent performance on both SMT and NMT forward translation systems." @default.
• W3082714809 created "2020-09-08" @default.
• W3082714809 creator A5027070750 @default.
• W3082714809 creator A5035934226 @default.
• W3082714809 creator A5056922715 @default.
• W3082714809 date "2020-11-01" @default.
• W3082714809 modified "2023-10-17" @default.
• W3082714809 title "Revisiting Round-trip Translation for Quality Estimation." @default.
• W3082714809 cites W1836793741 @default.
• W3082714809 cites W1988843054 @default.
• W3082714809 cites W2087735403 @default.
• W3082714809 cites W2101105183 @default.
• W3082714809 cites W2149327368 @default.
• W3082714809 cites W2165169506 @default.
• W3082714809 cites W2171904031 @default.
• W3082714809 cites W2250342921 @default.
• W3082714809 cites W2741049976 @default.
• W3082714809 cites W2903188467 @default.
• W3082714809 cites W2916835973 @default.
• W3082714809 cites W2932893307 @default.
• W3082714809 cites W2936597270 @default.
• W3082714809 cites W2963341956 @default.
• W3082714809 cites W2963403868 @default.
• W3082714809 cites W2963532001 @default.
• W3082714809 cites W2970791445 @default.
• W3082714809 cites W2970986500 @default.
• W3082714809 cites W2971120958 @default.
• W3082714809 cites W2987395887 @default.
• W3082714809 cites W2996403597 @default.
• W3082714809 cites W3104033643 @default.
• W3082714809 cites W3214359265 @default.
• W3082714809 hasPublicationYear "2020" @default.
• W3082714809 type Work @default.
• W3082714809 sameAs 3082714809 @default.
• W3082714809 citedByCount "3" @default.
• W3082714809 countsByYear W30827148092021 @default.
• W3082714809 crossrefType "journal-article" @default.
• W3082714809 hasAuthorship W3082714809A5027070750 @default.
• W3082714809 hasAuthorship W3082714809A5035934226 @default.
• W3082714809 hasAuthorship W3082714809A5056922715 @default.
• W3082714809 hasConcept C103278499 @default.
• W3082714809 hasConcept C104317684 @default.
• W3082714809 hasConcept C105580179 @default.
• W3082714809 hasConcept C111472728 @default.
• W3082714809 hasConcept C115961682 @default.
• W3082714809 hasConcept C119857082 @default.
• W3082714809 hasConcept C130318100 @default.
• W3082714809 hasConcept C135784402 @default.
• W3082714809 hasConcept C138885662 @default.
• W3082714809 hasConcept C148526163 @default.
• W3082714809 hasConcept C149364088 @default.
• W3082714809 hasConcept C154945302 @default.
• W3082714809 hasConcept C162324750 @default.
• W3082714809 hasConcept C176217482 @default.
• W3082714809 hasConcept C185592680 @default.
• W3082714809 hasConcept C187736073 @default.
• W3082714809 hasConcept C203005215 @default.
• W3082714809 hasConcept C204321447 @default.
• W3082714809 hasConcept C21547014 @default.
• W3082714809 hasConcept C24687705 @default.
• W3082714809 hasConcept C2524010 @default.
• W3082714809 hasConcept C2777530160 @default.
• W3082714809 hasConcept C2779530757 @default.
• W3082714809 hasConcept C2780451532 @default.
• W3082714809 hasConcept C28490314 @default.
• W3082714809 hasConcept C33923547 @default.
• W3082714809 hasConcept C41008148 @default.
• W3082714809 hasConcept C55493867 @default.
• W3082714809 hasConcept C622187 @default.
• W3082714809 hasConcept C90805587 @default.
• W3082714809 hasConceptScore W3082714809C103278499 @default.
• W3082714809 hasConceptScore W3082714809C104317684 @default.
• W3082714809 hasConceptScore W3082714809C105580179 @default.
• W3082714809 hasConceptScore W3082714809C111472728 @default.
• W3082714809 hasConceptScore W3082714809C115961682 @default.
• W3082714809 hasConceptScore W3082714809C119857082 @default.
• W3082714809 hasConceptScore W3082714809C130318100 @default.
• W3082714809 hasConceptScore W3082714809C135784402 @default.
• W3082714809 hasConceptScore W3082714809C138885662 @default.
• W3082714809 hasConceptScore W3082714809C148526163 @default.
• W3082714809 hasConceptScore W3082714809C149364088 @default.
• W3082714809 hasConceptScore W3082714809C154945302 @default.
• W3082714809 hasConceptScore W3082714809C162324750 @default.
• W3082714809 hasConceptScore W3082714809C176217482 @default.
• W3082714809 hasConceptScore W3082714809C185592680 @default.
• W3082714809 hasConceptScore W3082714809C187736073 @default.
• W3082714809 hasConceptScore W3082714809C203005215 @default.
• W3082714809 hasConceptScore W3082714809C204321447 @default.
• W3082714809 hasConceptScore W3082714809C21547014 @default.
• W3082714809 hasConceptScore W3082714809C24687705 @default.
• W3082714809 hasConceptScore W3082714809C2524010 @default.
• W3082714809 hasConceptScore W3082714809C2777530160 @default.
• W3082714809 hasConceptScore W3082714809C2779530757 @default.
• W3082714809 hasConceptScore W3082714809C2780451532 @default.
• W3082714809 hasConceptScore W3082714809C28490314 @default.
• W3082714809 hasConceptScore W3082714809C33923547 @default.
• W3082714809 hasConceptScore W3082714809C41008148 @default.
• W3082714809 hasConceptScore W3082714809C55493867 @default.

• next