Login / Signup
Improving Parallel Data Identification using Iteratively Refined Sentence Alignments and Bilingual Mappings of Pre-trained Language Models.
Chi-kiu Lo
Eric Joanis
Published in:
WMT@EMNLP (2020)
Keyphrases
</>
language model
data sets
language modeling
training data
prior knowledge
document retrieval
bayesian networks
natural language
probabilistic model
small number