Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation.
Peerat LimkonchotiwatWannaphong PhatthiyaphaibunRaheem SarwarEkapol ChuangsuwanichSarana NutanongPublished in: ACL/IJCNLP (Findings) (2021)
Keyphrases
- word segmentation
- n gram
- text classification
- language independent
- chinese text
- handwriting recognition
- word recognition
- chinese word segmentation
- pos tagging
- language modeling
- document analysis
- cross lingual
- chinese text retrieval
- unknown words
- handwritten documents
- transfer learning
- information retrieval
- image analysis
- high dimensional
- training set
- image processing
- machine learning
- data mining
- neural network