Ad-Hoc Information Retrieval
26 papers with code • 1 benchmarks • 0 datasets
Ad-hoc information retrieval refers to the task of returning information resources related to a user query formulated in natural language.
In order to adopt deep learning for information retrieval, models are needed that can capture all relevant information required to assess the relevance of a document to a given user query.
Neural IR models, such as DRMM and PACRR, have achieved strong results by successfully capturing relevance matching signals.
Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair.