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