Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation.
Beomsu KimSeokjun SeoSeungju HanEnkhbayar ErdeneeBuru ChangPublished in: EMNLP (Findings) (2021)
Keyphrases
- generative model
- open domain
- retrieval model
- prior knowledge
- probabilistic model
- mixture model
- information retrieval
- language model
- document retrieval
- language modeling
- information extraction
- information retrieval systems
- knowledge representation
- query expansion
- test collection
- em algorithm
- vector space
- expectation maximization
- question answering
- tf idf