Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315706547> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4315706547 abstract "Advancements in unsupervised machine translation have enabled the development of machine translation systems that can translate between languages for which there is not an abundance of parallel data available. We explored unsupervised machine translation between Mandarin Chinese and Cantonese. Despite the vast number of native speakers of Cantonese, there is still no large-scale corpus for the language, due to the fact that Cantonese is primarily used for oral communication. The key contributions of our project include: 1. The creation of a new corpus containing approximately 1 million Cantonese sentences, and 2. A large-scale comparison across different model architectures, tokenization schemes, and embedding structures. Our best model trained with character-based tokenization and a Transformer architecture achieved a character-level BLEU of 25.1 when translating from Mandarin to Cantonese and of 24.4 when translating from Cantonese to Mandarin. In this paper we discuss our research process, experiments, and results." @default.
- W4315706547 created "2023-01-12" @default.
- W4315706547 creator A5004552621 @default.
- W4315706547 creator A5050419964 @default.
- W4315706547 creator A5054275201 @default.
- W4315706547 creator A5058986709 @default.
- W4315706547 creator A5074399703 @default.
- W4315706547 date "2023-01-10" @default.
- W4315706547 modified "2023-09-27" @default.
- W4315706547 title "Unsupervised Mandarin-Cantonese Machine Translation" @default.
- W4315706547 doi "https://doi.org/10.48550/arxiv.2301.03971" @default.
- W4315706547 hasPublicationYear "2023" @default.
- W4315706547 type Work @default.
- W4315706547 citedByCount "0" @default.
- W4315706547 crossrefType "posted-content" @default.
- W4315706547 hasAuthorship W4315706547A5004552621 @default.
- W4315706547 hasAuthorship W4315706547A5050419964 @default.
- W4315706547 hasAuthorship W4315706547A5054275201 @default.
- W4315706547 hasAuthorship W4315706547A5058986709 @default.
- W4315706547 hasAuthorship W4315706547A5074399703 @default.
- W4315706547 hasBestOaLocation W43157065471 @default.
- W4315706547 hasConcept C121332964 @default.
- W4315706547 hasConcept C138885662 @default.
- W4315706547 hasConcept C138954614 @default.
- W4315706547 hasConcept C154945302 @default.
- W4315706547 hasConcept C165801399 @default.
- W4315706547 hasConcept C176982825 @default.
- W4315706547 hasConcept C203005215 @default.
- W4315706547 hasConcept C204321447 @default.
- W4315706547 hasConcept C24687705 @default.
- W4315706547 hasConcept C2524010 @default.
- W4315706547 hasConcept C2780861071 @default.
- W4315706547 hasConcept C28490314 @default.
- W4315706547 hasConcept C33923547 @default.
- W4315706547 hasConcept C41008148 @default.
- W4315706547 hasConcept C41895202 @default.
- W4315706547 hasConcept C62520636 @default.
- W4315706547 hasConcept C66322947 @default.
- W4315706547 hasConceptScore W4315706547C121332964 @default.
- W4315706547 hasConceptScore W4315706547C138885662 @default.
- W4315706547 hasConceptScore W4315706547C138954614 @default.
- W4315706547 hasConceptScore W4315706547C154945302 @default.
- W4315706547 hasConceptScore W4315706547C165801399 @default.
- W4315706547 hasConceptScore W4315706547C176982825 @default.
- W4315706547 hasConceptScore W4315706547C203005215 @default.
- W4315706547 hasConceptScore W4315706547C204321447 @default.
- W4315706547 hasConceptScore W4315706547C24687705 @default.
- W4315706547 hasConceptScore W4315706547C2524010 @default.
- W4315706547 hasConceptScore W4315706547C2780861071 @default.
- W4315706547 hasConceptScore W4315706547C28490314 @default.
- W4315706547 hasConceptScore W4315706547C33923547 @default.
- W4315706547 hasConceptScore W4315706547C41008148 @default.
- W4315706547 hasConceptScore W4315706547C41895202 @default.
- W4315706547 hasConceptScore W4315706547C62520636 @default.
- W4315706547 hasConceptScore W4315706547C66322947 @default.
- W4315706547 hasLocation W43157065471 @default.
- W4315706547 hasOpenAccess W4315706547 @default.
- W4315706547 hasPrimaryLocation W43157065471 @default.
- W4315706547 hasRelatedWork W1484029852 @default.
- W4315706547 hasRelatedWork W1512718085 @default.
- W4315706547 hasRelatedWork W1585034923 @default.
- W4315706547 hasRelatedWork W2157780473 @default.
- W4315706547 hasRelatedWork W2167662847 @default.
- W4315706547 hasRelatedWork W3107474891 @default.
- W4315706547 hasRelatedWork W3111475895 @default.
- W4315706547 hasRelatedWork W3118680649 @default.
- W4315706547 hasRelatedWork W4313011231 @default.
- W4315706547 hasRelatedWork W2610387714 @default.
- W4315706547 isParatext "false" @default.
- W4315706547 isRetracted "false" @default.
- W4315706547 workType "article" @default.