Explore a cutting-edge approach to neural ranking in this 11-minute conference talk from SIGIR 2024. Delve into the innovative GUITAR (Gradient Pruning toward Fast Neural Ranking) method presented by authors Weijie Zhao, Shulong Tan, and Ping Li. Learn how this technique aims to enhance the efficiency of search algorithms through gradient pruning, potentially revolutionizing the speed and performance of neural ranking systems. Gain insights into the latest advancements in information retrieval and machine learning as applied to search technology.
GUITAR: Gradient Pruning toward Fast Neural Ranking - Efficiency for Search
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M1.3 [fp] GUITAR: Gradient Pruning toward Fast Neural Ranking
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Neural Passage Quality Estimation for Static Pruning - Efficiency for Search
-
Multi-granular Adversarial Attacks Against Black-box Neural Ranking Models - Lecture 1
-
Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
-
A Taxation Perspective for Fair Re-ranking - SIGIR 2024
-
Ranked List Truncation for Large Language Model-based Re-Ranking - Efficiency for Search
-
Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models - Session M1.1
