Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952032790> ?p ?o ?g. }
- W2952032790 abstract "Unsupervised word translation from non-parallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the impressive success of the recent techniques, they suffer from the typical drawbacks of generative adversarial models: sensitivity to hyper-parameters, long training time and lack of interpretability. In this paper, we make the observation that two sufficiently similar distributions can be aligned correctly with iterative matching methods. We present a novel method that first aligns the second moment of the word distributions of the two languages and then iteratively refines the alignment. Extensive experiments on word translation of European and Non-European languages show that our method achieves better performance than recent state-of-the-art deep adversarial approaches and is competitive with the supervised baseline. It is also efficient, easy to parallelize on CPU and interpretable." @default.
- W2952032790 created "2019-06-27" @default.
- W2952032790 creator A5047455929 @default.
- W2952032790 creator A5078102229 @default.
- W2952032790 date "2018-01-18" @default.
- W2952032790 modified "2023-10-01" @default.
- W2952032790 title "Non-Adversarial Unsupervised Word Translation" @default.
- W2952032790 cites W1626233182 @default.
- W2952032790 cites W1731081199 @default.
- W2952032790 cites W1968691112 @default.
- W2952032790 cites W2041232209 @default.
- W2952032790 cites W2058659201 @default.
- W2952032790 cites W2072976288 @default.
- W2952032790 cites W2099471712 @default.
- W2952032790 cites W2102749417 @default.
- W2952032790 cites W2121415745 @default.
- W2952032790 cites W2126725946 @default.
- W2952032790 cites W2140406733 @default.
- W2952032790 cites W2250229103 @default.
- W2952032790 cites W2294774419 @default.
- W2952032790 cites W2331128040 @default.
- W2952032790 cites W2605287558 @default.
- W2952032790 cites W2608015370 @default.
- W2952032790 cites W2737057113 @default.
- W2952032790 cites W2741602058 @default.
- W2952032790 cites W2762484717 @default.
- W2952032790 cites W2786378416 @default.
- W2952032790 cites W2949769632 @default.
- W2952032790 cites W2950359962 @default.
- W2952032790 cites W2950577311 @default.
- W2952032790 cites W2951939904 @default.
- W2952032790 cites W2952190837 @default.
- W2952032790 cites W2952566282 @default.
- W2952032790 cites W2963061446 @default.
- W2952032790 hasPublicationYear "2018" @default.
- W2952032790 type Work @default.
- W2952032790 sameAs 2952032790 @default.
- W2952032790 citedByCount "14" @default.
- W2952032790 countsByYear W29520327902018 @default.
- W2952032790 countsByYear W29520327902019 @default.
- W2952032790 countsByYear W29520327902020 @default.
- W2952032790 crossrefType "posted-content" @default.
- W2952032790 hasAuthorship W2952032790A5047455929 @default.
- W2952032790 hasAuthorship W2952032790A5078102229 @default.
- W2952032790 hasConcept C104317684 @default.
- W2952032790 hasConcept C105580179 @default.
- W2952032790 hasConcept C105795698 @default.
- W2952032790 hasConcept C108583219 @default.
- W2952032790 hasConcept C119857082 @default.
- W2952032790 hasConcept C149364088 @default.
- W2952032790 hasConcept C154945302 @default.
- W2952032790 hasConcept C162324750 @default.
- W2952032790 hasConcept C165064840 @default.
- W2952032790 hasConcept C185592680 @default.
- W2952032790 hasConcept C187736073 @default.
- W2952032790 hasConcept C203005215 @default.
- W2952032790 hasConcept C204321447 @default.
- W2952032790 hasConcept C2524010 @default.
- W2952032790 hasConcept C2780451532 @default.
- W2952032790 hasConcept C2781067378 @default.
- W2952032790 hasConcept C2988773926 @default.
- W2952032790 hasConcept C33923547 @default.
- W2952032790 hasConcept C37736160 @default.
- W2952032790 hasConcept C39890363 @default.
- W2952032790 hasConcept C41008148 @default.
- W2952032790 hasConcept C55493867 @default.
- W2952032790 hasConcept C90805587 @default.
- W2952032790 hasConceptScore W2952032790C104317684 @default.
- W2952032790 hasConceptScore W2952032790C105580179 @default.
- W2952032790 hasConceptScore W2952032790C105795698 @default.
- W2952032790 hasConceptScore W2952032790C108583219 @default.
- W2952032790 hasConceptScore W2952032790C119857082 @default.
- W2952032790 hasConceptScore W2952032790C149364088 @default.
- W2952032790 hasConceptScore W2952032790C154945302 @default.
- W2952032790 hasConceptScore W2952032790C162324750 @default.
- W2952032790 hasConceptScore W2952032790C165064840 @default.
- W2952032790 hasConceptScore W2952032790C185592680 @default.
- W2952032790 hasConceptScore W2952032790C187736073 @default.
- W2952032790 hasConceptScore W2952032790C203005215 @default.
- W2952032790 hasConceptScore W2952032790C204321447 @default.
- W2952032790 hasConceptScore W2952032790C2524010 @default.
- W2952032790 hasConceptScore W2952032790C2780451532 @default.
- W2952032790 hasConceptScore W2952032790C2781067378 @default.
- W2952032790 hasConceptScore W2952032790C2988773926 @default.
- W2952032790 hasConceptScore W2952032790C33923547 @default.
- W2952032790 hasConceptScore W2952032790C37736160 @default.
- W2952032790 hasConceptScore W2952032790C39890363 @default.
- W2952032790 hasConceptScore W2952032790C41008148 @default.
- W2952032790 hasConceptScore W2952032790C55493867 @default.
- W2952032790 hasConceptScore W2952032790C90805587 @default.
- W2952032790 hasLocation W29520327901 @default.
- W2952032790 hasOpenAccess W2952032790 @default.
- W2952032790 hasPrimaryLocation W29520327901 @default.
- W2952032790 hasRelatedWork W2126725946 @default.
- W2952032790 hasRelatedWork W2294774419 @default.
- W2952032790 hasRelatedWork W2493916176 @default.
- W2952032790 hasRelatedWork W2561995736 @default.
- W2952032790 hasRelatedWork W2593768305 @default.
- W2952032790 hasRelatedWork W2740132093 @default.
- W2952032790 hasRelatedWork W2741602058 @default.