Comparing two analyzers of Japanese corpora for helping linguists: MeCab and Sagace (Comparaison de deux outils d'analyse de corpus japonais pour l'aide au linguiste, Sagace et Mecab) [in French].
Raoul BlinPublished in: TALN (2) (2014)
Keyphrases
- text corpora
- computational linguistics
- wide coverage
- annotated corpus
- document corpus
- text data
- topic segmentation
- text corpus
- natural language processing
- statistical machine translation
- specific domains
- hand crafted
- japanese language
- word frequency
- text mining
- parallel corpus
- open domain
- manually annotated
- machine learning
- parallel corpora
- word pairs
- text classification
- information extraction
- linguistic patterns
- artificial intelligence
- word frequencies