A Test Collection of Synthetic Documents for Training Rankers: ChatGPT vs. Human Experts.
Arian AskariMohammad AliannejadiEvangelos KanoulasSuzan VerbernePublished in: CIKM (2023)
Keyphrases
- test collection
- human experts
- relevant documents
- document collections
- relevance judgments
- information retrieval
- relevance judgements
- relevance assessments
- retrieval systems
- learning to rank
- retrieval effectiveness
- document set
- information retrieval systems
- trec web track
- average precision
- document retrieval
- retrieval model
- language model
- domain experts
- search tasks
- trec test collections
- pseudo relevance feedback
- post processing
- chinese web
- query terms
- ranked list
- classification rules
- trec web
- supervised learning
- xml retrieval
- machine learning
- document clustering
- query expansion
- knowledge base
- human relevance judgments
- search engine
- metadata
- ir evaluation
- expert systems
- association rules
- domain knowledge
- knowledge acquisition
- document representation
- vector space model