Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction.
Danushka BollegalaRyuichi KiryoKosuke TsujinoHaruki YukawaPublished in: CoRR (2020)
Keyphrases
- language independent
- language specific
- machine translation
- n gram
- cross lingual
- text classification
- text retrieval
- cross language
- word level
- natural language
- data mining
- active learning
- natural language processing
- question answering
- semi automatic
- text categorization
- co occurrence
- knowledge discovery
- artificial intelligence