YODA System for WMT16 Shared Task: Bilingual Document Alignment.
Aswarth Abhilash DaraYiu-Chang LinPublished in: WMT (2016)
Keyphrases
- word alignment
- document classification
- information retrieval systems
- sentence pairs
- document images
- word level
- document collections
- retrieval systems
- text documents
- document retrieval
- information retrieval
- chinese english
- cross lingual
- machine translation
- parallel texts
- source language
- web documents
- keywords
- document representation
- cross language information retrieval
- document clustering
- statistical machine translation
- document analysis
- wordnet
- parallel corpora
- semantic information
- text collections
- tf idf
- cross language
- information extraction
- named entity recognition