A Novel Word Segmentation Approach for Written Languages with Word Boundary Markers.
Han-Cheol ChoDo-Gil LeeJung-Tae LeePontus StenetorpJun'ichi TsujiiHae-Chang RimPublished in: ACL/IJCNLP (2) (2009)
Keyphrases
- word segmentation
- language independent
- cross lingual
- n gram
- word recognition
- indian languages
- word level
- chinese word segmentation
- handwriting recognition
- chinese text
- text classification
- language specific
- out of vocabulary
- machine translation
- unknown words
- pos tagging
- chinese text retrieval
- document analysis
- cross language
- text retrieval
- machine learning
- language modeling
- knowledge representation
- search engine