Büyük ölçekli aramada verimliliği artırmak: Gelenekselden sinirsel getirme sistemlerine

Read full text Summarise with VIRAT
Authors: Erman Yafay
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Efficient retrieval of relevant documents from massive collections remains an essen- tial challenge in Information Retrieval (IR). Modern search engines face immense computational demands, requiring novel approaches that reduce resource usage with- out sacrificing retrieval effectiveness. This thesis makes significant contributions to improving search efficiency through three distinct methods. First, we introduce in- novative document reordering techniques specifically optimized for dynamic pruning algorithms. Our proposed methods achieve up to 1.33x speed-up in query processing, accompanied by negligible increases in index size and minimal impact on retrieval quality. Second, we present novel sparse centroid retrieval strategies tailored to the ColBERT neural retrieval model. These techniques accelerate ColBERT-based re- trieval by up to 4.6x while maintaining high effectiveness and minimal additional indexing overhead. Lastly, we propose novel static pruning methods for ColBERT document embeddings that eliminate approximately one-third of the tokens from in- dexed documents without any loss in retrieval effectiveness. Critically, our pruning methods require no separate training stages, ensuring ease of integration into existing retrieval systems. Collectively, these contributions offer substantial advancements in retrieval efficiency, making large-scale IR systems faster, more scalable, and econom- ically sustainable.

Fields of Study & Subjects

Information Retrieval and Search Behavior Algorithms and Data Compression Topic Modeling

Publication details

Journal / source
OpenMETU (Middle East Technical University)
Publication date
23 March 2026
Language
EN
Document type
Thesis