『EP07 - Efficient Neural Search: Rethinking Inverted Indexes for Learned Sparse Representations. With Dr. Franco Maria Nardini』のカバーアート

EP07 - Efficient Neural Search: Rethinking Inverted Indexes for Learned Sparse Representations. With Dr. Franco Maria Nardini

EP07 - Efficient Neural Search: Rethinking Inverted Indexes for Learned Sparse Representations. With Dr. Franco Maria Nardini

無料で聴く

ポッドキャストの詳細を見る

In this episode of targz, Franco Maria Nardini, Research Director at ISTI-CNR, explains Seismic, a two-level inverted index for fast retrieval over learned sparse representations. It beats graph-based state-of-the-art methods by up to 3.5x in speed with comparable memory, and opens new directions in inference-free and edge retrieval.

Want to know more? checkout the paper: Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations

adbl_web_anon_alc_button_suppression_c
まだレビューはありません