Crosslingual Embeddings are Essential in UNMT for distant languages: An English to IndoAryan Case Study.
Tamali BanerjeeV. Rudra MurthyPushpak BhattacharyaPublished in: MTSummit (1) (2021)
Keyphrases
- case study
- cross lingual
- target language
- language identification
- english text
- language specific
- native language
- machine translation
- query translation
- automatically generated
- language independent
- statistical machine translation
- arabic language
- language resources
- english language
- manually constructed
- european languages
- dimensionality reduction
- spoken language
- machine translation system
- bilingual dictionaries
- multilingual information retrieval
- comparable corpora
- indian languages
- source language
- parallel corpora
- real world
- cross language
- language modeling
- software development
- language learning
- vector space
- databases
- natural language
- correlation clustering
- answer questions
- manifold learning
- parallel corpus
- text to speech
- expressive power
- design process
- character n grams
- distance measure
- euclidean space
- text summarization