Construction of an English Dependency Corpus incorporating Compound Function Words.
Akihiko KatoHiroyuki ShindoYuji MatsumotoPublished in: LREC (2016)
Keyphrases
- english words
- multiword
- person names
- unknown words
- parallel corpus
- training corpus
- link grammar
- stop words
- word frequencies
- word sense
- semantic roles
- open domain
- lexical units
- wide coverage
- part of speech
- text corpora
- broad coverage
- statistical machine translation
- compound words
- pos tagging
- word level
- n gram
- natural language text
- sentence pairs
- linguistic information
- word alignment
- machine translation system
- word pairs
- cross lingual
- language specific
- natural language
- lexical features
- translation model
- word co occurrence
- noun phrases
- language independent
- word sense disambiguation
- machine translation
- text classification