Matches in SemOpenAlex for { <https://semopenalex.org/work/W2006258004> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2006258004 endingPage "493" @default.
- W2006258004 startingPage "483" @default.
- W2006258004 abstract "Coherence that ties sentences of a text into a meaningfully connected structure is of great importance to text generation and translation. In this paper, we propose topic-based coherence models to produce coherence for document translation, in terms of the continuity of sentence topics in a text. We automatically extract a coherence chain for each source text to be translated. Based on the extracted source coherence chain, we adopt a maximum entropy classifier to predict the target coherence chain that defines a linear topic structure for the target document. We build two topic-based coherence models on the predicted target coherence chain: 1) a word level coherence model that helps the decoder select coherent word translations and 2) a phrase level coherence model that guides the decoder to select coherent phrase translations. We integrate the two models into a state-of-the-art phrase-based machine translation system. Experiments on large-scale training data show that our coherence models achieve substantial improvements over both the baseline and models that are built on either document topics or sentence topics obtained under the assumption of direct topic correspondence between the source and target side. Additionally, further evaluations on translation outputs suggest that target translations generated by our coherence models are more coherent and similar to reference translations than those generated by the baseline." @default.
- W2006258004 created "2016-06-24" @default.
- W2006258004 creator A5006795236 @default.
- W2006258004 creator A5012727269 @default.
- W2006258004 creator A5055232825 @default.
- W2006258004 date "2015-03-01" @default.
- W2006258004 modified "2023-09-23" @default.
- W2006258004 title "Topic-Based Coherence Modeling for Statistical Machine Translation" @default.
- W2006258004 cites W1969743400 @default.
- W2006258004 cites W2001412575 @default.
- W2006258004 cites W2030987872 @default.
- W2006258004 cites W2033593667 @default.
- W2006258004 cites W2078861931 @default.
- W2006258004 cites W2105577415 @default.
- W2006258004 cites W2129224106 @default.
- W2006258004 cites W2140676672 @default.
- W2006258004 cites W2146574666 @default.
- W2006258004 cites W2153653739 @default.
- W2006258004 cites W4237791300 @default.
- W2006258004 cites W4300672009 @default.
- W2006258004 doi "https://doi.org/10.1109/taslp.2015.2395254" @default.
- W2006258004 hasPublicationYear "2015" @default.
- W2006258004 type Work @default.
- W2006258004 sameAs 2006258004 @default.
- W2006258004 citedByCount "29" @default.
- W2006258004 countsByYear W20062580042015 @default.
- W2006258004 countsByYear W20062580042016 @default.
- W2006258004 countsByYear W20062580042017 @default.
- W2006258004 countsByYear W20062580042018 @default.
- W2006258004 countsByYear W20062580042019 @default.
- W2006258004 countsByYear W20062580042021 @default.
- W2006258004 countsByYear W20062580042022 @default.
- W2006258004 crossrefType "journal-article" @default.
- W2006258004 hasAuthorship W2006258004A5006795236 @default.
- W2006258004 hasAuthorship W2006258004A5012727269 @default.
- W2006258004 hasAuthorship W2006258004A5055232825 @default.
- W2006258004 hasConcept C105795698 @default.
- W2006258004 hasConcept C120012220 @default.
- W2006258004 hasConcept C154945302 @default.
- W2006258004 hasConcept C203005215 @default.
- W2006258004 hasConcept C204321447 @default.
- W2006258004 hasConcept C2776224158 @default.
- W2006258004 hasConcept C2777530160 @default.
- W2006258004 hasConcept C2781181686 @default.
- W2006258004 hasConcept C33923547 @default.
- W2006258004 hasConcept C41008148 @default.
- W2006258004 hasConcept C95623464 @default.
- W2006258004 hasConceptScore W2006258004C105795698 @default.
- W2006258004 hasConceptScore W2006258004C120012220 @default.
- W2006258004 hasConceptScore W2006258004C154945302 @default.
- W2006258004 hasConceptScore W2006258004C203005215 @default.
- W2006258004 hasConceptScore W2006258004C204321447 @default.
- W2006258004 hasConceptScore W2006258004C2776224158 @default.
- W2006258004 hasConceptScore W2006258004C2777530160 @default.
- W2006258004 hasConceptScore W2006258004C2781181686 @default.
- W2006258004 hasConceptScore W2006258004C33923547 @default.
- W2006258004 hasConceptScore W2006258004C41008148 @default.
- W2006258004 hasConceptScore W2006258004C95623464 @default.
- W2006258004 hasIssue "3" @default.
- W2006258004 hasLocation W20062580041 @default.
- W2006258004 hasOpenAccess W2006258004 @default.
- W2006258004 hasPrimaryLocation W20062580041 @default.
- W2006258004 hasRelatedWork W1597901428 @default.
- W2006258004 hasRelatedWork W1964739745 @default.
- W2006258004 hasRelatedWork W2108705322 @default.
- W2006258004 hasRelatedWork W2115634880 @default.
- W2006258004 hasRelatedWork W2277993829 @default.
- W2006258004 hasRelatedWork W2399585936 @default.
- W2006258004 hasRelatedWork W2507994462 @default.
- W2006258004 hasRelatedWork W2757524561 @default.
- W2006258004 hasRelatedWork W2790548820 @default.
- W2006258004 hasRelatedWork W3090543350 @default.
- W2006258004 hasVolume "23" @default.
- W2006258004 isParatext "false" @default.
- W2006258004 isRetracted "false" @default.
- W2006258004 magId "2006258004" @default.
- W2006258004 workType "article" @default.