Web Content Filtering Through Knowledge Distillation of Large Language Models.
Tamás VörösSean Paul BergeronKonstantin BerlinPublished in: CAMLIS (2023)
Keyphrases
- language model
- web content
- language modeling
- query expansion
- website
- probabilistic model
- n gram
- speech recognition
- document retrieval
- retrieval model
- information retrieval
- language modelling
- test collection
- web pages
- statistical language models
- document ranking
- context sensitive
- translation model
- semantic browsing
- language model for information retrieval
- web search engines
- social media
- vector space model
- smoothing methods
- machine learning
- okapi bm