Parallel Text Identification Using Lexical and Corpus Features for the English-Maori Language Pair.
Mahsa MohagheghAbdolhossein SarrafzadehPublished in: ICMLA (2016)
Keyphrases
- lexical features
- syntactic features
- english text
- lexical information
- linguistic information
- word pairs
- semantic roles
- english language
- linguistic analysis
- broad coverage
- natural language
- word sense
- machine translation system
- natural language processing
- parallel corpus
- comparable corpora
- unknown words
- computational linguistics
- language learning
- recognizing textual entailment
- bilingual dictionaries
- native language
- text to speech
- textual features
- open domain
- feature set
- keywords
- english words
- link grammar
- text corpus
- linguistic features
- target language
- parallel corpora
- syntactic categories
- multiword
- natural language text
- co occurrence
- semantic information
- information retrieval
- syntactic information
- wordnet
- text documents
- manually constructed
- text retrieval
- cross lingual
- textual entailment
- stop words
- language specific
- text mining
- controlled natural language
- word level