Login / Signup

Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings.

Benjamin MarieAtsushi Fujita
Published in: ACL (2) (2017)
Keyphrases
  • data sets
  • raw data
  • data analysis
  • database
  • data points
  • training data
  • natural language
  • high dimensional data
  • word alignment
  • information retrieval
  • keywords
  • probabilistic model
  • domain specific
  • sentence level