FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3145583208> ?p ?o ?g. }

• W3145583208 endingPage "17" @default.
• W3145583208 startingPage "1" @default.
• W3145583208 abstract "Unsupervised neural machine translation (UNMT) has achieved remarkable results for several language pairs, such as French–English and German–English. Most previous studies have focused on modeling UNMT systems; few studies have investigated the effect of UNMT on specific languages. In this article, we first empirically investigate UNMT for four diverse language pairs (French/German/Chinese/Japanese–English). We confirm that the performance of UNMT in translation tasks for similar language pairs (French/German–English) is dramatically better than for distant language pairs (Chinese/Japanese–English). We empirically show that the lack of shared words and different word orderings are the main reasons that lead UNMT to underperform in Chinese/Japanese–English. Based on these findings, we propose several methods, including artificial shared words and pre-ordering, to improve the performance of UNMT for distant language pairs. Moreover, we propose a simple general method to improve translation performance for all these four language pairs. The existing UNMT model can generate a translation of a reasonable quality after a few training epochs owing to a denoising mechanism and shared latent representations. However, learning shared latent representations restricts the performance of translation in both directions, particularly for distant language pairs, while denoising dramatically delays convergence by continuously modifying the training data. To avoid these problems, we propose a simple, yet effective and efficient, approach that (like UNMT) relies solely on monolingual corpora: pseudo-data-based unsupervised neural machine translation. Experimental results for these four language pairs show that our proposed methods significantly outperform UNMT baselines." @default.
• W3145583208 created "2021-04-13" @default.
• W3145583208 creator A5006323375 @default.
• W3145583208 creator A5013373263 @default.
• W3145583208 creator A5021667085 @default.
• W3145583208 creator A5023868584 @default.
• W3145583208 creator A5033318800 @default.
• W3145583208 creator A5038560914 @default.
• W3145583208 creator A5070812231 @default.
• W3145583208 date "2021-01-31" @default.
• W3145583208 modified "2023-09-27" @default.
• W3145583208 title "Unsupervised Neural Machine Translation for Similar and Distant Language Pairs" @default.
• W3145583208 cites W2036291627 @default.
• W3145583208 cites W2162245945 @default.
• W3145583208 cites W2493916176 @default.
• W3145583208 cites W2623037479 @default.
• W3145583208 cites W2886095922 @default.
• W3145583208 cites W2890007195 @default.
• W3145583208 cites W2932618389 @default.
• W3145583208 cites W2950428495 @default.
• W3145583208 cites W2963047628 @default.
• W3145583208 cites W2963206679 @default.
• W3145583208 cites W2963216553 @default.
• W3145583208 cites W2963260202 @default.
• W3145583208 cites W2963443683 @default.
• W3145583208 cites W2963532104 @default.
• W3145583208 cites W2963661253 @default.
• W3145583208 cites W2963804993 @default.
• W3145583208 cites W2963922633 @default.
• W3145583208 cites W2964013027 @default.
• W3145583208 cites W2964266061 @default.
• W3145583208 cites W2964707311 @default.
• W3145583208 cites W2971254483 @default.
• W3145583208 cites W2997574889 @default.
• W3145583208 doi "https://doi.org/10.1145/3418059" @default.
• W3145583208 hasPublicationYear "2021" @default.
• W3145583208 type Work @default.
• W3145583208 sameAs 3145583208 @default.
• W3145583208 citedByCount "7" @default.
• W3145583208 countsByYear W31455832082021 @default.
• W3145583208 countsByYear W31455832082022 @default.
• W3145583208 countsByYear W31455832082023 @default.
• W3145583208 crossrefType "journal-article" @default.
• W3145583208 hasAuthorship W3145583208A5006323375 @default.
• W3145583208 hasAuthorship W3145583208A5013373263 @default.
• W3145583208 hasAuthorship W3145583208A5021667085 @default.
• W3145583208 hasAuthorship W3145583208A5023868584 @default.
• W3145583208 hasAuthorship W3145583208A5033318800 @default.
• W3145583208 hasAuthorship W3145583208A5038560914 @default.
• W3145583208 hasAuthorship W3145583208A5070812231 @default.
• W3145583208 hasConcept C104317684 @default.
• W3145583208 hasConcept C105580179 @default.
• W3145583208 hasConcept C111472728 @default.
• W3145583208 hasConcept C130597682 @default.
• W3145583208 hasConcept C137293760 @default.
• W3145583208 hasConcept C138885662 @default.
• W3145583208 hasConcept C149364088 @default.
• W3145583208 hasConcept C154775046 @default.
• W3145583208 hasConcept C154945302 @default.
• W3145583208 hasConcept C185592680 @default.
• W3145583208 hasConcept C203005215 @default.
• W3145583208 hasConcept C204321447 @default.
• W3145583208 hasConcept C24687705 @default.
• W3145583208 hasConcept C2780586882 @default.
• W3145583208 hasConcept C41008148 @default.
• W3145583208 hasConcept C41895202 @default.
• W3145583208 hasConcept C55493867 @default.
• W3145583208 hasConcept C90805587 @default.
• W3145583208 hasConceptScore W3145583208C104317684 @default.
• W3145583208 hasConceptScore W3145583208C105580179 @default.
• W3145583208 hasConceptScore W3145583208C111472728 @default.
• W3145583208 hasConceptScore W3145583208C130597682 @default.
• W3145583208 hasConceptScore W3145583208C137293760 @default.
• W3145583208 hasConceptScore W3145583208C138885662 @default.
• W3145583208 hasConceptScore W3145583208C149364088 @default.
• W3145583208 hasConceptScore W3145583208C154775046 @default.
• W3145583208 hasConceptScore W3145583208C154945302 @default.
• W3145583208 hasConceptScore W3145583208C185592680 @default.
• W3145583208 hasConceptScore W3145583208C203005215 @default.
• W3145583208 hasConceptScore W3145583208C204321447 @default.
• W3145583208 hasConceptScore W3145583208C24687705 @default.
• W3145583208 hasConceptScore W3145583208C2780586882 @default.
• W3145583208 hasConceptScore W3145583208C41008148 @default.
• W3145583208 hasConceptScore W3145583208C41895202 @default.
• W3145583208 hasConceptScore W3145583208C55493867 @default.
• W3145583208 hasConceptScore W3145583208C90805587 @default.
• W3145583208 hasIssue "1" @default.
• W3145583208 hasLocation W31455832081 @default.
• W3145583208 hasOpenAccess W3145583208 @default.
• W3145583208 hasPrimaryLocation W31455832081 @default.
• W3145583208 hasRelatedWork W1512718085 @default.
• W3145583208 hasRelatedWork W1674885750 @default.
• W3145583208 hasRelatedWork W193726211 @default.
• W3145583208 hasRelatedWork W1978161643 @default.
• W3145583208 hasRelatedWork W2167662847 @default.
• W3145583208 hasRelatedWork W2167761917 @default.
• W3145583208 hasRelatedWork W2289817541 @default.
• W3145583208 hasRelatedWork W3037986478 @default.

• next