Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors.
Cong ZhouYong DaiDuyu TangEnbo ZhaoZhangyin FengLi KuangShuming ShiPublished in: CoRR (2022)
Keyphrases
- word segmentation
- chinese word segmentation
- chinese text
- unknown words
- co occurrence
- insertions and deletions
- recognition errors
- n gram
- english text
- english chinese
- hidden markov models
- text mining
- speech recognition
- automatic detection
- keywords
- morphological analysis
- word level
- information retrieval
- machine learning