Hierarchical Document Encoder for Parallel Corpus Mining.
Mandy GuoYinfei YangKeith StevensDaniel CerHeming GeYun-Hsuan SungBrian StropeRay KurzweilPublished in: WMT (1) (2019)
Keyphrases
- parallel corpus
- cross lingual
- web documents
- machine translation
- knowledge discovery
- text mining
- source language
- information retrieval
- document clustering
- document classification
- cross language information retrieval
- data mining
- relevant documents
- information retrieval systems
- word alignment
- statistical machine translation
- query translation
- document collections
- text documents
- document representation
- vector space model
- keywords
- language independent
- image retrieval
- target language
- semantic information
- test collection
- semantic space
- document retrieval
- machine learning