Applying EM to compute document relevance from crowdsourced pair preferences
Traditional Information Retrieval (IR) systems evaluate over absolute relevance judgments or multi- grade judgments by hiring expert assessors. More recently there has been considerable interest in inferring document relevance, for which no true relevance labels are available, based on noisy crowdso...
| Published: |
|
|---|---|
| Online Access: | http://hdl.handle.net/2047/d20003141 |