Continual Learning of Long Topic Sequences in
Neural Information Retrieval - abstract
Thomas Gerald1 , Laure Soulier1
1
    Sorbonne Université, CNRS, ISIR, F-75005 Paris, France


                                         Abstract
                                         In information retrieval (IR) systems, trends and users’ interests may change over time, altering either
                                         the distribution of requests or contents to be recommended. Since neural ranking approaches heavily
                                         depend on the training data, it is crucial to understand the transfer capacity of recent IR approaches to
                                         address new domains in the long term. In this paper, we first propose a dataset based upon the MSMarco
                                         corpus aiming at modeling a long stream of topics as well as IR property-driven controlled settings. We
                                         then in-depth analyze the ability of recent neural IR models while continually learning those streams.
                                         Our empirical study highlights in which particular cases catastrophic forgetting occurs (e.g., level of
                                         similarity between tasks, peculiarities on text length, and ways of learning models) to provide directions
                                         in terms of model design. The integral version of the paper has been published at ECIR 2022.

                                         Keywords
                                         Continual learning, information retrieval, Neural ranking models




CIRCLE’22: Conference of the Information Retrieval Communities in Europe, July 04–07, 2022, Samatan, Gers, France
$ thomas.gerald@isir.upmc.fr (T. Gerald); soulier@isir.upmc.fr (L. Soulier)
                                       © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
    CEUR
    Workshop
    Proceedings
                  http://ceur-ws.org
                  ISSN 1613-0073
                                       CEUR Workshop Proceedings (CEUR-WS.org)