Inducing a Malay Lexicon from an Unlabelled Dataset Using Word Embeddings.
Ian H. J. HoHui-Ngo GohYi-Fei TanPublished in: IEA/AIE (2022)
Keyphrases
- handwritten words
- sentence level
- natural language
- n gram
- linguistic knowledge
- vector space
- dimensionality reduction
- co occurrence
- information retrieval
- word sense disambiguation
- low dimensional
- semi supervised learning
- benchmark datasets
- database
- word recognition
- statistical machine translation
- manifold learning
- text corpus
- concept space
- part of speech
- synthetic datasets
- machine learning