FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2250479947> ?p ?o ?g. }

• W2250479947 abstract "In the past decade, statistical machine translation (SMT) has been advanced from word-based SMT to phraseand syntax-based SMT. Although this advancement produces significant improvements in BLEU scores, crucial meaning errors and lack of cross-sentence connections at discourse level still hurt the quality of SMT-generated translations. More recently, we have witnessed two active movements in SMT research: one towards combining semantics and SMT in attempt to generate not only grammatical but also meaningpreserved translations, and the other towards exploring discourse knowledge for document-level machine translation in order to capture intersentence dependencies. The emergence of semantic SMT are due to the combination of two factors: the necessity of semantic modeling in SMT and the renewed interest of designing models tailored to relevant NLP/SMT applications in the semantics community. The former is represented by recent numerous studies on exploring word sense disambiguation, semantic role labeling, bilingual semantic representations as well as semantic evaluation for SMT. The latter is reflected in CoNLL shared tasks, SemEval and SenEval exercises in recent years. The need of capturing cross-sentence dependencies for document-level SMT triggers the resurgent interest of modeling translation from the perspective of discourse. Discourse phenomena, such as coherent relations, discourse topics, lexical cohesion that are beyond the scope of conventional sentence-level n-grams, have been recently considered and explored in the context of SMT. This tutorial aims at providing a timely and combined introduction of such recent work along these two trends as discourse is inherently connected with semantics. The tutorial has three parts. The first part critically reviews the phraseand syntax-based SMT. The second part is devoted to the lines of research oriented to semantic SMT, including a brief introduction of semantics, lexical and shallow semantics tailored to SMT, semantic representations in SMT, semantically motivated evaluation as well as advanced topics on deep semantic learning for SMT. The third part is dedicated to recent work on SMT with discourse, including a brief review on discourse studies from linguistics and computational viewpoints, discourse research from monolingual to multilingual, discourse-based SMT and a few advanced topics. The tutorial is targeted for researchers in the SMT, semantics and discourse communities. In particular, the expected audience comes from two groups: 1) Researchers and students in the SMT community who want to design cutting-edge models and algorithms for semantic SMT with various semantic knowledge and representations, and who would like to advance SMT from sentence-bysentence translation to document-level translation with discourse information; 2) Researchers and students from the semantics and discourse community who are interested in developing models and methods and adapting them to SMT." @default.
• W2250479947 created "2016-06-24" @default.
• W2250479947 creator A5053204257 @default.
• W2250479947 creator A5055232825 @default.
• W2250479947 date "2014-01-01" @default.
• W2250479947 modified "2023-09-23" @default.
• W2250479947 title "Semantics, Discourse and Statistical Machine Translation" @default.
• W2250479947 doi "https://doi.org/10.3115/v1/p14-6007" @default.
• W2250479947 hasPublicationYear "2014" @default.
• W2250479947 type Work @default.
• W2250479947 sameAs 2250479947 @default.
• W2250479947 citedByCount "0" @default.
• W2250479947 crossrefType "proceedings-article" @default.
• W2250479947 hasAuthorship W2250479947A5053204257 @default.
• W2250479947 hasAuthorship W2250479947A5055232825 @default.
• W2250479947 hasConcept C104054115 @default.
• W2250479947 hasConcept C151730666 @default.
• W2250479947 hasConcept C154945302 @default.
• W2250479947 hasConcept C162324750 @default.
• W2250479947 hasConcept C178790620 @default.
• W2250479947 hasConcept C184337299 @default.
• W2250479947 hasConcept C185592680 @default.
• W2250479947 hasConcept C187736073 @default.
• W2250479947 hasConcept C199360897 @default.
• W2250479947 hasConcept C203005215 @default.
• W2250479947 hasConcept C204321447 @default.
• W2250479947 hasConcept C2777530160 @default.
• W2250479947 hasConcept C2779343474 @default.
• W2250479947 hasConcept C2780451532 @default.
• W2250479947 hasConcept C41008148 @default.
• W2250479947 hasConcept C44572571 @default.
• W2250479947 hasConcept C60048249 @default.
• W2250479947 hasConcept C67277372 @default.
• W2250479947 hasConcept C86803240 @default.
• W2250479947 hasConceptScore W2250479947C104054115 @default.
• W2250479947 hasConceptScore W2250479947C151730666 @default.
• W2250479947 hasConceptScore W2250479947C154945302 @default.
• W2250479947 hasConceptScore W2250479947C162324750 @default.
• W2250479947 hasConceptScore W2250479947C178790620 @default.
• W2250479947 hasConceptScore W2250479947C184337299 @default.
• W2250479947 hasConceptScore W2250479947C185592680 @default.
• W2250479947 hasConceptScore W2250479947C187736073 @default.
• W2250479947 hasConceptScore W2250479947C199360897 @default.
• W2250479947 hasConceptScore W2250479947C203005215 @default.
• W2250479947 hasConceptScore W2250479947C204321447 @default.
• W2250479947 hasConceptScore W2250479947C2777530160 @default.
• W2250479947 hasConceptScore W2250479947C2779343474 @default.
• W2250479947 hasConceptScore W2250479947C2780451532 @default.
• W2250479947 hasConceptScore W2250479947C41008148 @default.
• W2250479947 hasConceptScore W2250479947C44572571 @default.
• W2250479947 hasConceptScore W2250479947C60048249 @default.
• W2250479947 hasConceptScore W2250479947C67277372 @default.
• W2250479947 hasConceptScore W2250479947C86803240 @default.
• W2250479947 hasLocation W22504799471 @default.
• W2250479947 hasOpenAccess W2250479947 @default.
• W2250479947 hasPrimaryLocation W22504799471 @default.
• W2250479947 hasRelatedWork W1578472035 @default.
• W2250479947 hasRelatedWork W1751837507 @default.
• W2250479947 hasRelatedWork W2045438809 @default.
• W2250479947 hasRelatedWork W2143210573 @default.
• W2250479947 hasRelatedWork W2186166348 @default.
• W2250479947 hasRelatedWork W2252147974 @default.
• W2250479947 hasRelatedWork W2900308591 @default.
• W2250479947 hasRelatedWork W2901270804 @default.
• W2250479947 hasRelatedWork W2902604592 @default.
• W2250479947 hasRelatedWork W2921267133 @default.
• W2250479947 hasRelatedWork W2935580023 @default.
• W2250479947 hasRelatedWork W2965362971 @default.
• W2250479947 hasRelatedWork W3013612165 @default.
• W2250479947 hasRelatedWork W3036733871 @default.
• W2250479947 hasRelatedWork W3046553216 @default.
• W2250479947 hasRelatedWork W3087256401 @default.
• W2250479947 hasRelatedWork W3102752580 @default.
• W2250479947 hasRelatedWork W3119632397 @default.
• W2250479947 hasRelatedWork W829120923 @default.
• W2250479947 hasRelatedWork W177250740 @default.
• W2250479947 isParatext "false" @default.
• W2250479947 isRetracted "false" @default.
• W2250479947 magId "2250479947" @default.
• W2250479947 workType "article" @default.