Findings of the WMT 2016 Bilingual Document Alignment Shared Task.
Christian BuckPhilipp KoehnPublished in: WMT (2016)
Keyphrases
- word alignment
- document classification
- sentence pairs
- document images
- web documents
- word level
- document collections
- information retrieval
- retrieval systems
- information retrieval systems
- document retrieval
- machine translation
- cross lingual
- text documents
- case study
- source language
- vector space model
- parallel texts
- parallel corpora
- cross language
- document clustering
- document representation
- semantic role labeling
- parallel corpus
- test set
- tf idf
- language independent
- document analysis
- statistical machine translation
- keywords
- relevant documents
- web pages
- probabilistic model