Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains.
Erkan BasarIris HendrickxEmiel KrahmerGert-Jan de BruijnTibor BossePublished in: ICAART (1) (2022)
Keyphrases
- language model
- open domain
- language modeling
- probabilistic model
- information extraction
- document retrieval
- information retrieval
- n gram
- statistical language models
- retrieval model
- language modelling
- query expansion
- question answering
- test collection
- smoothing methods
- query terms
- pseudo relevance feedback
- document ranking
- independence assumption
- vector space model
- relevance model
- statistical language modeling
- language models for information retrieval
- text classification