An Empirical Study of Active Learning with Support Vector Machines for Japanese Word Segmentation.
Manabu SassanoPublished in: ACL (2002)
Keyphrases
- word segmentation
- active learning
- n gram
- word recognition
- language independent
- text classification
- handwriting recognition
- semi supervised
- chinese text
- chinese word segmentation
- chinese text retrieval
- learning algorithm
- supervised learning
- machine learning
- random sampling
- unlabeled data
- document analysis
- language modeling
- relevance feedback
- word level
- cross lingual
- sparse data
- semi supervised learning
- labeled data
- pos tagging
- training set