Discrete Diffusion Language Modeling by Estimating the Ratios of the Data Distribution.
Aaron LouChenlin MengStefano ErmonPublished in: CoRR (2023)
Keyphrases
- data distribution
- language modeling
- language model
- information retrieval
- retrieval model
- n gram
- query expansion
- cross lingual
- data streams
- probabilistic model
- high dimensional data
- statistical language models
- text classification
- data points
- index structure
- improvements in retrieval effectiveness
- digital libraries
- web documents
- data sets
- test collection
- information retrieval systems
- dimensionality reduction
- image processing
- nearest neighbor
- continuous data
- image data
- dirichlet prior
- knowledge discovery