A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages.
Pedro Javier Ortiz SuárezLaurent RomaryBenoît SagotPublished in: CoRR (2020)
Keyphrases
- bilingual dictionaries
- target language
- cross lingual
- statistical machine translation
- source language
- machine translation system
- european languages
- machine translation
- language specific
- query translation
- parallel corpus
- multilingual information retrieval
- translation model
- language independent
- word alignment
- character n grams
- word order
- cross language information retrieval
- english chinese
- n gram
- cross lingual information retrieval
- cross language
- resource allocation
- multiword
- parallel corpora
- word segmentation
- comparable corpora
- indian languages
- grammar induction
- natural language
- english text
- dimensionality reduction
- linguistic resources
- question answering
- co occurrence
- word pairs
- word sense disambiguation
- chinese english
- vector space
- query expansion
- low dimensional
- tasks in natural language processing
- compound words
- feature selection
- pos taggers
- language model
- text categorization
- spoken document retrieval
- out of vocabulary