Skip to main content


Information Retrieval Journal

Information Retrieval Journal OnlineFirst articles


ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation

Human–computer conversation is an active research topic in natural language processing. One of the representative methods to build conversation systems uses the sequence-to-sequence (Seq2seq) model through neural networks. However, with limited …

21-09-2019 | Axiomatic Thinking for Information Retrieval

Evaluation measures for quantification: an axiomatic approach

Quantification is the task of estimating, given a set $$\sigma $$ σ of unlabelled items and a set of classes $${\mathcal {C}}=\{c_{1}, \ldots , c_{|{\mathcal {C}}|}\}$$ C = { c 1 , … , c | C | } , the prevalence (or “relative frequency”) in …

04-09-2019 | Axiomatic Thinking for Information Retrieval

How do interval scales help us with better understanding IR evaluation measures?

Evaluation measures are the basis for quantifying the performance of IR systems and the way in which their values can be processed to perform statistical analyses depends on the scales on which these measures are defined. For example, mean and …

13-08-2019 | eCommerce Search and Recommendation

Deep cross-platform product matching in e-commerce

Online shopping has become more and more popular in recent years, which leads to a prosperity on online platforms. Generally, the identical products are provided by many sellers on multiple platforms. Thus the comparison between products on …


Fewer topics? A million topics? Both?! On topics subsets in test collections

When evaluating IR run effectiveness using a test collection, a key question is: What search topics should be used? We explore what happens to measurement accuracy when the number of topics in a test collection is reduced, using the Million Query …

Current Publications

About this journal

The journal provides an international forum for the publication of theory, algorithms, and experiments across the broad area of information retrieval. Topics of interest include search, indexing, analysis, and evaluation for applications such as text archives, social and streaming media, recommender systems, and the web. Research results published in the journal typically address the problems that arise for user-oriented tasks where the meaning as well as the explicit content of the data is of interest.

Information Retrieval Journal features theoretical, experimental and applied papers. Theoretical papers report a significant conceptual advance in the design of algorithms or other processes for some information retrieval task. Experimental papers detail a test of one or more theoretical ideas in a laboratory or natural setting. Application papers cover successful application of some already established technique to a significant real world problem involving information retrieval.

Information retrieval overlaps with a variety of technical and behavioral fields. As a result, the journal includes papers which unify concepts across several traditional disciplinary boundaries, with specific application to problems of information retrieval.

Additional information

Premium Partner

    Image Credits