Policy-Gradient Training of Language Models for Ranking.
Ge GaoJonathan D. ChangClaire CardieKianté BrantleyThorsten JoachimsPublished in: CoRR (2023)
Keyphrases
- language model
- document ranking
- policy gradient
- smoothing methods
- language modeling
- document retrieval
- query specific
- n gram
- relevance model
- probabilistic model
- query expansion
- retrieval model
- language models for information retrieval
- information retrieval
- speech recognition
- ranking functions
- test collection
- web search
- training set
- machine learning
- optimal control
- pseudo relevance feedback
- supervised learning
- hidden markov models