Improve word segmentation performance from unknown language by decreasing meaningless segmentation.
Shinya MatsushitaHaruhiko TakaseToshiaki TakanoKatsuko TomotsuguPublished in: CIIS (2023)
Keyphrases
- word segmentation
- chinese text retrieval
- chinese word segmentation
- n gram
- word recognition
- text classification
- handwriting recognition
- document analysis
- chinese text
- language modeling
- language independent
- pos tagging
- word level
- machine translation
- pattern recognition
- image segmentation
- target language
- natural language
- data mining
- cross lingual
- artificial intelligence