Abstract
This tutorial presents explainable information retrieval (ExIR), an emerging area focused on fostering responsible and trustworthy deployment of machine learning systems in the context of information retrieval. As the field has rapidly evolved in the past 4-5 years, numerous approaches have been proposed that focus on different access modes, stakeholders, and model development stages. This tutorial aims to introduce IR-centric notions, classification, and evaluation styles in ExIR, while focusing on IR-specific tasks such as ranking, text classification, and learning-to-rank systems. We will delve into method families and their adaptations to IR, extensively covering post-hoc methods, axiomatic and probing approaches, and recent advances in interpretability-by-design approaches. We will also discuss ExIR applications for different stakeholders, such as researchers, practitioners, and end-users, in contexts like web search, patent and legal search, and high-stakes decision-making tasks. To facilitate practical understanding, we will provide a hands-on session on applying ExIR methods, reducing the entry barrier for students, researchers, and practitioners alike.
Original language | English |
---|---|
Title of host publication | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval |
Publisher | Association for Computing Machinery (ACM) |
Pages | 3448-3451 |
Number of pages | 4 |
ISBN (Electronic) | 9781450394086 |
DOIs | |
Publication status | Published - 2023 |
Event | 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023 - Taipei, Taiwan Duration: 23 Jul 2023 → 27 Jul 2023 |
Publication series
Name | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval |
---|
Conference
Conference | 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023 |
---|---|
Country/Territory | Taiwan |
City | Taipei |
Period | 23/07/23 → 27/07/23 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- axiomatic ranking
- explainable information retrieval
- interpretable by design
- posthoc interpretability
- probing