Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages.
Idris AbdulmuminAuwal Abubakar KhalidShamsuddeen Hassan MuhammadIbrahim Said AhmadLukman Jibril AliyuBabangida SaniBala Mairiga AbduljalilSani Ahmad HassanPublished in: CoRR (2023)
Keyphrases
- language independent
- sentence pairs
- word level
- multi lingual
- cross lingual
- parallel corpus
- machine translation system
- text summarization
- multilingual information retrieval
- target language
- language resources
- multilingual documents
- resource allocation
- semi automatic
- text generation
- digital libraries
- language specific
- cross language information retrieval
- n gram
- queueing networks
- query translation
- word alignment
- cross language
- resource management
- vector space
- lexical knowledge
- arabic language
- text classification
- natural language
- semantic role labeling
- dynamic time warping
- comparable corpora