Weighted Sampling for Masked Language Modeling.
Linhan ZhangQian ChenWen WangChong DengXin CaoKongzhang HaoYuxin JiangWei WangPublished in: ICASSP (2023)
Keyphrases
- language modeling
- language model
- query expansion
- retrieval model
- information retrieval
- n gram
- probabilistic model
- cross lingual
- text classification
- statistical language models
- improvements in retrieval effectiveness
- term weighting
- retrieval effectiveness
- text mining
- trec collections
- comparable corpora
- statistical language modeling
- document retrieval
- relevance model
- test collection
- generative model
- model selection
- principal component analysis
- feature extraction