Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study.
Tamali BanerjeeV. Rudra MurthyPushpak BhattacharyyaPublished in: CoRR (2021)
Keyphrases
- case study
- language identification
- cross lingual
- target language
- english text
- native language
- statistical machine translation
- multilingual information retrieval
- query translation
- spoken language
- automatically generated
- machine translation
- language independent
- language specific
- arabic language
- language resources
- comparable corpora
- source language
- manually constructed
- word forms
- natural language
- databases
- bilingual dictionaries
- expressive power
- english language
- indian languages
- language learning
- parallel corpora
- real world
- linguistic resources
- word level
- machine translation system
- cross language information retrieval
- cross language
- manifold learning
- low dimensional
- software development
- word order
- text summarization
- character n grams
- vector space
- monolingual retrieval