English-French Document Alignment Based on Keywords and Statistical Translation.
Marek MedvedMilos JakubícekVojtech KovárPublished in: WMT (2016)
Keyphrases
- keywords
- word level
- machine translation
- word alignment
- source language
- mono lingual
- statistical machine translation
- multilingual retrieval
- query translation
- target language
- cross language
- keyword extraction
- web documents
- sentence pairs
- relevant documents
- document collections
- document images
- cross language information retrieval
- foreign language
- cross lingual
- language independent
- cross language retrieval
- machine translation system
- information retrieval
- natural language
- index terms
- parallel corpus
- monolingual retrieval
- search engine
- document retrieval
- text documents
- semantic information
- user queries
- document set
- text retrieval
- parallel corpora
- dublin city university
- language learning
- keyword search
- structured queries
- cross language ir
- information retrieval systems
- relevant content
- english chinese
- english words
- language resources
- chinese english
- retrieve documents
- comparable corpora
- web pages
- similar documents
- natural language processing
- bilingual dictionaries
- query expansion
- document clustering
- noun phrases
- pronominal anaphora
- multilingual information retrieval
- text summarization
- document representation
- information access
- retrieval systems
- test collection
- n gram
- language model