Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962723321> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2962723321 abstract "This work explores neural machine translation between Myanmar (Burmese) and Rakhine (Arakanese). Rakhine is a language closely related to Myanmar, often considered a dialect. We implemented three prominent neural machine translation (NMT) systems: recurrent neural networks (RNN), transformer, and convolutional neural networks (CNN). The systems were evaluated on a Myanmar-Rakhine parallel text corpus developed by us. In addition, two types of word segmentation schemes for word embeddings were studied: Word-BPE and Syllable-BPE segmentation. Our experimental results clearly show that the highest quality NMT and statistical machine translation (SMT) performances are obtained with Syllable-BPE segmentation for both types of translations. If we focus on NMT, we find that the transformer with Word-BPE segmentation outperforms CNN and RNN for both Myanmar-Rakhine and Rakhine-Myanmar translation. However, CNN with Syllable-BPE segmentation obtains a higher score than the RNN and transformer." @default.
- W2962723321 created "2019-07-30" @default.
- W2962723321 creator A5020194074 @default.
- W2962723321 creator A5035058548 @default.
- W2962723321 creator A5083674619 @default.
- W2962723321 date "2019-01-01" @default.
- W2962723321 modified "2023-09-23" @default.
- W2962723321 title "Neural Machine Translation between" @default.
- W2962723321 cites W1535005341 @default.
- W2962723321 cites W1598299201 @default.
- W2962723321 cites W1618137506 @default.
- W2962723321 cites W1753482797 @default.
- W2962723321 cites W1902237438 @default.
- W2962723321 cites W2101105183 @default.
- W2962723321 cites W2130942839 @default.
- W2962723321 cites W2134800885 @default.
- W2962723321 cites W2146574666 @default.
- W2962723321 cites W2153508793 @default.
- W2962723321 cites W2186615578 @default.
- W2962723321 cites W2194775991 @default.
- W2962723321 cites W2251222643 @default.
- W2962723321 cites W2402302915 @default.
- W2962723321 cites W2766894774 @default.
- W2962723321 cites W2778814079 @default.
- W2962723321 cites W2805910418 @default.
- W2962723321 cites W2962784628 @default.
- W2962723321 cites W2963403868 @default.
- W2962723321 cites W2963970792 @default.
- W2962723321 cites W2964265128 @default.
- W2962723321 cites W2964308564 @default.
- W2962723321 cites W3130872697 @default.
- W2962723321 cites W46679369 @default.
- W2962723321 cites W1525783482 @default.
- W2962723321 doi "https://doi.org/10.18653/v1/w19-1408" @default.
- W2962723321 hasPublicationYear "2019" @default.
- W2962723321 type Work @default.
- W2962723321 sameAs 2962723321 @default.
- W2962723321 citedByCount "1" @default.
- W2962723321 countsByYear W29627233212020 @default.
- W2962723321 crossrefType "proceedings-article" @default.
- W2962723321 hasAuthorship W2962723321A5020194074 @default.
- W2962723321 hasAuthorship W2962723321A5035058548 @default.
- W2962723321 hasAuthorship W2962723321A5083674619 @default.
- W2962723321 hasConcept C109089402 @default.
- W2962723321 hasConcept C119599485 @default.
- W2962723321 hasConcept C127413603 @default.
- W2962723321 hasConcept C147168706 @default.
- W2962723321 hasConcept C154945302 @default.
- W2962723321 hasConcept C165801399 @default.
- W2962723321 hasConcept C203005215 @default.
- W2962723321 hasConcept C204321447 @default.
- W2962723321 hasConcept C28490314 @default.
- W2962723321 hasConcept C41008148 @default.
- W2962723321 hasConcept C50644808 @default.
- W2962723321 hasConcept C520968082 @default.
- W2962723321 hasConcept C66322947 @default.
- W2962723321 hasConcept C81363708 @default.
- W2962723321 hasConcept C89600930 @default.
- W2962723321 hasConceptScore W2962723321C109089402 @default.
- W2962723321 hasConceptScore W2962723321C119599485 @default.
- W2962723321 hasConceptScore W2962723321C127413603 @default.
- W2962723321 hasConceptScore W2962723321C147168706 @default.
- W2962723321 hasConceptScore W2962723321C154945302 @default.
- W2962723321 hasConceptScore W2962723321C165801399 @default.
- W2962723321 hasConceptScore W2962723321C203005215 @default.
- W2962723321 hasConceptScore W2962723321C204321447 @default.
- W2962723321 hasConceptScore W2962723321C28490314 @default.
- W2962723321 hasConceptScore W2962723321C41008148 @default.
- W2962723321 hasConceptScore W2962723321C50644808 @default.
- W2962723321 hasConceptScore W2962723321C520968082 @default.
- W2962723321 hasConceptScore W2962723321C66322947 @default.
- W2962723321 hasConceptScore W2962723321C81363708 @default.
- W2962723321 hasConceptScore W2962723321C89600930 @default.
- W2962723321 hasLocation W29627233211 @default.
- W2962723321 hasOpenAccess W2962723321 @default.
- W2962723321 hasPrimaryLocation W29627233211 @default.
- W2962723321 hasRelatedWork W112480583 @default.
- W2962723321 hasRelatedWork W1445015017 @default.
- W2962723321 hasRelatedWork W1836529743 @default.
- W2962723321 hasRelatedWork W2139671364 @default.
- W2962723321 hasRelatedWork W2415731916 @default.
- W2962723321 hasRelatedWork W2920938200 @default.
- W2962723321 hasRelatedWork W2962723321 @default.
- W2962723321 hasRelatedWork W3034342478 @default.
- W2962723321 hasRelatedWork W3107474891 @default.
- W2962723321 hasRelatedWork W1887844490 @default.
- W2962723321 isParatext "false" @default.
- W2962723321 isRetracted "false" @default.
- W2962723321 magId "2962723321" @default.
- W2962723321 workType "article" @default.