← smac.pub home

Adaptive Re-Ranking as an Information-Seeking Agent

pdf bibtex workshop paper

Authors: Sean MacAvaney, Nicola Tonellotto, Craig Macdonald

Appeared in: First Workshop on Proactive and Agent-Supported Information Retrieval (PASIR@CIKM 2022)

DBLP conf/cikm/MacAvaneyTM22a Google Scholar 7wWfoDgAAAAJ:isC4tDSrTZIC Semantic Scholar 301d1d5d9feb129d7e1c940620916aa35a6a72d0 Enlighten 281840 smac.pub pasir2022-gagent


Re-ranking systems are typically limited by the recall of the initial retrieval function. A recent work proposed adaptive re-ranking, which modifies the re-ranking loop to progressively prioritise documents likely to receive high scores based on the highest scoring ones thus far. The original work framed this process as an incarnation of the well-established clustering hypothesis. In this work, we argue that the approach can also be framed as an information-seeking agent. From this perspective, we explore several variations of the graph-based adaptive re-ranking algorithm and find that there is substantial room for improvement by modifying the agent. However, the agents that we explore are more sensitive to the new parameters they introduce than the simple-yet-effective approach proposed in the original adaptive re-ranking work.

BibTeX @inproceedings{macavaney:pasir2022-gagent, author = {MacAvaney, Sean and Tonellotto, Nicola and Macdonald, Craig}, title = {Adaptive Re-Ranking as an Information-Seeking Agent}, booktitle = {First Workshop on Proactive and Agent-Supported Information Retrieval}, year = {2022} }