Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285261341> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4285261341 abstract "As high-quality Malay language resources are still a scarcity, cross lingual word embeddings make it possible for richer English resources to be leveraged for downstream Malay text classification tasks. This paper focuses on creating an English-Malay cross-lingual word embeddings using embedding alignment by exploiting existing language resources. We augmented the training bilingual lexicons using machine translation with the goal to improve the alignment precision of our cross-lingual word embeddings. We investigated the quality of the current state-of-the-art English-Malay bilingual lexicon and worked on improving its quality using Google Translate. We also examined the effect of Malay word coverage on the quality of cross-lingual word embeddings. Experimental results with a precision up till 28.17% show that the alignment precision of the cross-lingual word embeddings would inevitably degrade after 1-NN but a better seed lexicon and cleaner nearest neighbours can reduce the number of word pairs required to achieve satisfactory performance. As the English and Malay monolingual embeddings are pre-trained on informal language corpora, our proposed English-Malay embeddings alignment approach is also able to map non-standard Malay translations in the English nearest neighbours." @default.
- W4285261341 created "2022-07-14" @default.
- W4285261341 creator A5018089270 @default.
- W4285261341 creator A5056731846 @default.
- W4285261341 date "2022-01-01" @default.
- W4285261341 modified "2023-09-26" @default.
- W4285261341 title "English-Malay Cross-Lingual Embedding Alignment using Bilingual Lexicon Augmentation" @default.
- W4285261341 doi "https://doi.org/10.18653/v1/2022.acl-srw.16" @default.
- W4285261341 hasPublicationYear "2022" @default.
- W4285261341 type Work @default.
- W4285261341 citedByCount "0" @default.
- W4285261341 crossrefType "proceedings-article" @default.
- W4285261341 hasAuthorship W4285261341A5018089270 @default.
- W4285261341 hasAuthorship W4285261341A5056731846 @default.
- W4285261341 hasBestOaLocation W42852613411 @default.
- W4285261341 hasConcept C111472728 @default.
- W4285261341 hasConcept C138885662 @default.
- W4285261341 hasConcept C154945302 @default.
- W4285261341 hasConcept C204321447 @default.
- W4285261341 hasConcept C2776938241 @default.
- W4285261341 hasConcept C2777462759 @default.
- W4285261341 hasConcept C2778121359 @default.
- W4285261341 hasConcept C2779235283 @default.
- W4285261341 hasConcept C2779530757 @default.
- W4285261341 hasConcept C28490314 @default.
- W4285261341 hasConcept C41008148 @default.
- W4285261341 hasConcept C41608201 @default.
- W4285261341 hasConcept C41895202 @default.
- W4285261341 hasConcept C90805587 @default.
- W4285261341 hasConceptScore W4285261341C111472728 @default.
- W4285261341 hasConceptScore W4285261341C138885662 @default.
- W4285261341 hasConceptScore W4285261341C154945302 @default.
- W4285261341 hasConceptScore W4285261341C204321447 @default.
- W4285261341 hasConceptScore W4285261341C2776938241 @default.
- W4285261341 hasConceptScore W4285261341C2777462759 @default.
- W4285261341 hasConceptScore W4285261341C2778121359 @default.
- W4285261341 hasConceptScore W4285261341C2779235283 @default.
- W4285261341 hasConceptScore W4285261341C2779530757 @default.
- W4285261341 hasConceptScore W4285261341C28490314 @default.
- W4285261341 hasConceptScore W4285261341C41008148 @default.
- W4285261341 hasConceptScore W4285261341C41608201 @default.
- W4285261341 hasConceptScore W4285261341C41895202 @default.
- W4285261341 hasConceptScore W4285261341C90805587 @default.
- W4285261341 hasLocation W42852613411 @default.
- W4285261341 hasOpenAccess W4285261341 @default.
- W4285261341 hasPrimaryLocation W42852613411 @default.
- W4285261341 hasRelatedWork W2105950210 @default.
- W4285261341 hasRelatedWork W2335882425 @default.
- W4285261341 hasRelatedWork W2741602058 @default.
- W4285261341 hasRelatedWork W2949267551 @default.
- W4285261341 hasRelatedWork W2993300079 @default.
- W4285261341 hasRelatedWork W3031457336 @default.
- W4285261341 hasRelatedWork W3100772908 @default.
- W4285261341 hasRelatedWork W3107679445 @default.
- W4285261341 hasRelatedWork W4205951810 @default.
- W4285261341 hasRelatedWork W4385570592 @default.
- W4285261341 isParatext "false" @default.
- W4285261341 isRetracted "false" @default.
- W4285261341 workType "article" @default.