Sub-Character Tokenization for Chinese Pretrained Language Models.
Chenglei SiZhengyan ZhangYingfa ChenFanchao QiXiaozhi WangZhiyuan LiuYasheng WangQun LiuMaosong SunPublished in: Trans. Assoc. Comput. Linguistics (2023)
Keyphrases
- language model
- n gram
- chinese characters
- language modeling
- word segmentation
- probabilistic model
- document retrieval
- speech recognition
- information retrieval
- statistical language models
- test collection
- pseudo relevance feedback
- context sensitive
- query expansion
- named entities
- character recognition
- retrieval model
- document ranking
- language modelling
- text summarization
- relevance model
- ad hoc information retrieval
- smoothing methods
- cross language retrieval
- okapi bm
- language models for information retrieval
- document length
- translation model
- vector space model
- cross lingual
- chinese english
- information retrieval systems
- natural language processing