Leif Azzopardi and Jiqun Liu
Negar Arabzadeh, Chuan Meng, Mohammad Aliannejadi and Ebrahim Bagheri
Tutorial Abstract: Query Performance Prediction (QPP) is a crucial task in Information Retrieval (IR), focusing on estimating the quality of retrieval results for a given query without the need for human-labeled relevance judgments. This tutorial explores the core techniques developed for QPP over the years and their growing importance, particularly in the context of modern pre-trained models and large language models (LLMs). In addition to discussing traditional QPP methods, the tutorial highlights their application in emerging fields such as conversational search and multi-agent systems. While QPP research has made significant progress, its practical application in real-world search engines remains an area with room for further development.
Biography: Negar Arabzadeh is a fourth-year Ph.D. student at the University of Waterloo, where she focuses on ad-hoc search and conversational search in Information Retrieval.
Fernando Diaz, Andrew Drozdov, To Eun Kim, Alireza Salemi and Hamed Zamani
More information: retrieval-enhanced-ml.github.io/sigir-ap2024-tutorial/
Mahdis Saeedi, Christine Wong and Hossein Fani
Tutorial Abstract: Collaborative team recommendation involves selecting experts with specific skills to form teams that are likely to accomplish tasks successfully. This tutorial provides a taxonomy of team recommendation methods based on their algorithmic approaches, beginning with a comprehensive study of pioneering graph-based methods. It then explores the latest advancements in graph neural networks as cutting-edge approaches. The tutorial also includes unifying definitions, formulations, evaluation schemas, and details on training strategies, benchmarking datasets, and open-source tools. Finally, future research directions are discussed.
More information: fani-lab.github.io/OpeNTF/tutorial/sigir-ap24/
Andrew Yates, Carlos Lassance, Sean MacAvaney, Thong Nguyen and Yibin Lei
More information: lsr-tutorial.github.io
