A Syntactic-based Word Re-ordering for English-Vietnamese Statistical Machine Translation System.
Hong-Nhung Nguyen ThiDien DinhPublished in: PRICAI (2008)
Keyphrases
- machine translation system
- word alignment
- lexical information
- statistical machine translation
- natural language
- machine translation
- parallel corpus
- english chinese
- highly ambiguous
- parse tree
- word sense disambiguation
- stop words
- syntactic information
- english text
- cross lingual
- word order
- english words
- natural language text
- language specific
- word sense
- syntactic semantic
- linguistic knowledge
- bilingual dictionaries
- syntactic categories
- unknown words
- syntactic analysis
- dependency parser
- computing semantic relatedness
- word level
- parallel corpora
- noun phrases
- query translation
- compound words
- target language
- named entity recognizer
- semantic roles
- wordnet
- cross language information retrieval
- named entity recognition
- language learning
- training corpus
- source language
- natural language processing
- translation model
- co occurrence
- dependency parsing
- language independent
- semantic information
- lexico syntactic
- information extraction
- document clustering
- probabilistic context free grammars
- recognizing textual entailment
- cross language
- semantic analysis
- syntactic structures
- semantic role labeling
- answer questions
- english language