FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2080215139> ?p ?o ?g. }

• W2080215139 abstract "HighlightsAnalyzing the output of English to Persian machine translation systems.Presenting hybrid morphology generation using a parallel corpus.Using a set of linguistically motivated features.Making a model to predict six morphological features of the verb.Applying our model to the output of two MTs and improving the results. Languages such as English need to be morphologically analyzed in translation into morphologically rich languages such as Persian. Analyzing the output of English to Persian machine translation systems illustrates that Persian morphology comes with many challenges especially in the verb conjugation. In this paper, we investigate three ways to deal with the morphology of Persian verb in machine translation (MT): no morphology generation in statistical MT, rule-based morphology generation in rule-based MT and a hybrid-model-independent morphology generation. By model-independent we mean that it is not based on statistical or rule-based MT and could be applied to any English to Persian MT as a post-processor. We select Google translator (translate.google.com) to show the performance of a statistical MT without any morphology generation component for the verb conjugation. Rule-based morphology generation is implemented as a part of a rule-based MT. Finally, we enrich the rule-based approach by statistical methods and information to present a hybrid model. A set of linguistically motivated features are defined using both English and Persian linguistic knowledge obtained from a parallel corpus. Then we make a model to predict six morphological features of the verb in Persian using decision tree classifier and generate an inflected verb form. In a real translation process, by applying our model to the output of Google translator and a rule-based MT as a post-processor, we achieve an improvement of about 0.7% absolute BLEU score in the best case. When we are given the gold lemma in our reference experiments, using the most common feature values as a baseline shows an improvement of almost 2.8% absolute BLEU score on a test set containing 15K sentences." @default.
• W2080215139 created "2016-06-24" @default.
• W2080215139 creator A5055598777 @default.
• W2080215139 creator A5060351059 @default.
• W2080215139 date "2015-07-01" @default.
• W2080215139 modified "2023-09-24" @default.
• W2080215139 title "Using decision tree to hybrid morphology generation of Persian verb for English–Persian translation" @default.
• W2080215139 cites W1599588252 @default.
• W2080215139 cites W1605282883 @default.
• W2080215139 cites W1608448541 @default.
• W2080215139 cites W1619002 @default.
• W2080215139 cites W1869993023 @default.
• W2080215139 cites W192825427 @default.
• W2080215139 cites W2039289813 @default.
• W2080215139 cites W2053582137 @default.
• W2080215139 cites W2097606805 @default.
• W2080215139 cites W2113788796 @default.
• W2080215139 cites W2117262435 @default.
• W2080215139 cites W2117642127 @default.
• W2080215139 cites W2117873652 @default.
• W2080215139 cites W2126241965 @default.
• W2080215139 cites W2136094405 @default.
• W2080215139 cites W2140110038 @default.
• W2080215139 cites W2149706766 @default.
• W2080215139 cites W2152249239 @default.
• W2080215139 cites W2153653739 @default.
• W2080215139 cites W2156985047 @default.
• W2080215139 cites W2158468759 @default.
• W2080215139 cites W2163238067 @default.
• W2080215139 cites W2170464899 @default.
• W2080215139 cites W2176663335 @default.
• W2080215139 cites W2250332179 @default.
• W2080215139 cites W2251622336 @default.
• W2080215139 cites W2339416199 @default.
• W2080215139 cites W2341118687 @default.
• W2080215139 cites W2463396630 @default.
• W2080215139 cites W2504840837 @default.
• W2080215139 cites W2618735189 @default.
• W2080215139 cites W2893578842 @default.
• W2080215139 cites W82303372 @default.
• W2080215139 doi "https://doi.org/10.1016/j.csl.2014.10.005" @default.
• W2080215139 hasPublicationYear "2015" @default.
• W2080215139 type Work @default.
• W2080215139 sameAs 2080215139 @default.
• W2080215139 citedByCount "1" @default.
• W2080215139 countsByYear W20802151392018 @default.
• W2080215139 crossrefType "journal-article" @default.
• W2080215139 hasAuthorship W2080215139A5055598777 @default.
• W2080215139 hasAuthorship W2080215139A5060351059 @default.
• W2080215139 hasConcept C138885662 @default.
• W2080215139 hasConcept C149271511 @default.
• W2080215139 hasConcept C154945302 @default.
• W2080215139 hasConcept C203005215 @default.
• W2080215139 hasConcept C204321447 @default.
• W2080215139 hasConcept C24687705 @default.
• W2080215139 hasConcept C2776397901 @default.
• W2080215139 hasConcept C2776527531 @default.
• W2080215139 hasConcept C41008148 @default.
• W2080215139 hasConcept C41895202 @default.
• W2080215139 hasConcept C53893814 @default.
• W2080215139 hasConcept C84525736 @default.
• W2080215139 hasConcept C95623464 @default.
• W2080215139 hasConceptScore W2080215139C138885662 @default.
• W2080215139 hasConceptScore W2080215139C149271511 @default.
• W2080215139 hasConceptScore W2080215139C154945302 @default.
• W2080215139 hasConceptScore W2080215139C203005215 @default.
• W2080215139 hasConceptScore W2080215139C204321447 @default.
• W2080215139 hasConceptScore W2080215139C24687705 @default.
• W2080215139 hasConceptScore W2080215139C2776397901 @default.
• W2080215139 hasConceptScore W2080215139C2776527531 @default.
• W2080215139 hasConceptScore W2080215139C41008148 @default.
• W2080215139 hasConceptScore W2080215139C41895202 @default.
• W2080215139 hasConceptScore W2080215139C53893814 @default.
• W2080215139 hasConceptScore W2080215139C84525736 @default.
• W2080215139 hasConceptScore W2080215139C95623464 @default.
• W2080215139 hasLocation W20802151391 @default.
• W2080215139 hasOpenAccess W2080215139 @default.
• W2080215139 hasPrimaryLocation W20802151391 @default.
• W2080215139 hasRelatedWork W1599588252 @default.
• W2080215139 hasRelatedWork W192825427 @default.
• W2080215139 hasRelatedWork W1976156341 @default.
• W2080215139 hasRelatedWork W2006996732 @default.
• W2080215139 hasRelatedWork W2017802499 @default.
• W2080215139 hasRelatedWork W2087914695 @default.
• W2080215139 hasRelatedWork W2132779412 @default.
• W2080215139 hasRelatedWork W2156984567 @default.
• W2080215139 hasRelatedWork W2176663335 @default.
• W2080215139 hasRelatedWork W2218202018 @default.
• W2080215139 hasRelatedWork W2293400980 @default.
• W2080215139 hasRelatedWork W2396770587 @default.
• W2080215139 hasRelatedWork W2464775082 @default.
• W2080215139 hasRelatedWork W2790419658 @default.
• W2080215139 hasRelatedWork W2907310984 @default.
• W2080215139 hasRelatedWork W2910527610 @default.
• W2080215139 hasRelatedWork W2991404811 @default.
• W2080215139 hasRelatedWork W3089774903 @default.
• W2080215139 hasRelatedWork W3107505055 @default.
• W2080215139 hasRelatedWork W2186574089 @default.
• W2080215139 isParatext "false" @default.
• W2080215139 isRetracted "false" @default.

• next