Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation.
Shizhe DiaoRuijia XuHongjin SuYilei JiangYan SongTong ZhangPublished in: ACL/IJCNLP (1) (2021)
Keyphrases
- language model
- n gram
- language modeling
- document retrieval
- language modelling
- information retrieval
- cross domain
- probabilistic model
- bag of words
- speech recognition
- retrieval model
- labeled data
- statistical language modeling
- part of speech
- sentiment classification
- text classification
- query expansion
- pseudo relevance feedback
- word segmentation
- test collection
- document classification
- unlabeled data
- document ranking