Machine Translation Customization via Automatic Training Data Selection from the Web.

Thuy Vu Alessandro Moschitti

Published in: ECIR (1) (2021)

Keyphrases

machine translation
multilingual documents
training data
information extraction
natural language generation
language processing
natural language processing

cross lingual
statistical machine translation
language independent
word sense disambiguation
cross language information retrieval
target language

language resources
training set
learning algorithm
web pages
machine translation system
web documents

word alignment
chinese english
natural language
parallel corpora
information retrieval systems
tasks in natural language processing