A passage-based approach to learning to rank documents

Abstract

According to common relevance-judgments regimes, such as TREC’s, a document can be deemed relevant to a query even if it contains a very short passage of text with pertinent information. This fact has motivated work on passage-based document retrieval: document ranking methods that induce information from the document’s passages. However, the main source of passage-based information utilized was passage-query similarities. In this paper, we address the challenge of utilizing richer sources of passage-based information to improve document retrieval effectiveness. Specifically, we devise a suite of learning-to-rank-based document retrieval methods that utilize an effective ranking of passages produced in response to the query. Some of the methods quantify the ranking of the passages of a document. Others utilize the feature-based representation of the document’s passages. Empirical evaluation attests to the clear merits of our methods with respect to highly effective baselines. Our best performing method is based on learning a document ranking function using document-query features and passage-query features of the document’s passage most highly ranked; the passage-query features are those used to learn a highly effective passage ranker.