CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks.
Xiaoxi LiZhicheng DouYujia ZhouFangchao LiuPublished in: SIGIR (2024)
Keyphrases
- language model
- knowledge intensive
- language modeling
- knowledge acquisition
- n gram
- statistical machine translation
- document retrieval
- document level
- speech recognition
- probabilistic model
- multiword
- ad hoc information retrieval
- statistical language models
- smoothing methods
- query expansion
- retrieval model
- information retrieval
- test collection
- software development
- context sensitive
- language modelling
- law enforcement
- human resources
- pseudo relevance feedback
- relevance model
- information systems
- query specific
- dirichlet prior
- query terms
- mixture model
- knowledge management
- information technology
- social networks