Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking....
<p><strong>Tác giả:</strong> Laura Caspari, Kanishka Ghosh Dastidar, Michael Dinzinger, Jelena Mitrović, Michael Granitzer</p>
<p>Dense retrieval is commonly evaluated on benchmarks that represent each document with a single embedding, even though real-world retrieval systems often index long documents that require chunking. In these settings, the chosen chunking method not only affects retrieval quality, but also indexing throughput, query latency, and memory usage. Prior comparisons of chunking strategies have mainly focused on retrieval performance, leaving operational trade-offs underexplored. To address these issue...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3799682.3839948" target="_blank" rel="noopener">https://doi.org/10.1145/3799682.3839948</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3799682.3839948" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
