Machine Learning Ranking and INEX'05

Jean-Noël Vittaut (1) , Patrick Gallinari (1)

1 MALIRE - Machine Learning and Information Retrieval

We present a Machine Learning based ranking model which can automatically learn its parameters using a training set of annotated examples composed of queries and relevance judgments on a subset of the document elements. Our model improves the performance of a baseline Information Retrieval system by optimizing a ranking loss criterion and combining scores computed from doxels and from their local structural context. We analyze the performance of our algorithm on CO-Focussed and CO-Thourough tasks and compare it to the baseline model which is an adaptation of Okapi to Structured Information Retrieval.

Domaines: Informatique [cs]

Jean-Noël Vittaut, Patrick Gallinari. Machine Learning Ranking and INEX'05. INEX 2005 - 4th Workshop of the INitiative for the Evaluation of XML Retrieval, Nov 2005, Dagstuhl, Germany. pp.336-343, ⟨10.1007/978-3-540-34963-1_25⟩. ⟨hal-01490514⟩