Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian.
Alberto PoncelasJohanes EffendiPublished in: LoResMT@COLING (2022)
Keyphrases
- machine translation
- language resources
- language specific
- case study
- cross lingual
- target language
- parallel corpus
- multilingual documents
- comparable corpora
- natural language
- machine translation system
- cross language information retrieval
- similarity measure
- natural language processing
- training process
- language independent
- bilingual dictionaries
- statistical machine translation
- distance measure
- query translation
- similarity metric
- digital libraries
- programming language
- test set
- training set
- word alignment
- e learning
- multilingual information retrieval
- supervised learning
- broadcast news
- linguistic knowledge
- structural similarity
- semantic similarity
- similarity function
- distance function
- training examples
- training samples