EUVIMEDEUVIMED entdecken
Crossref

SeDA: Bridging the Gap between Efficient Syntactic and Precise Semantic Search of Similar Passages in Large Text Corpora

Pranay Mundra, Daniel Kocher, Martin Schäler, Nikolaus Augsten

Proceedings of the VLDB Endowment · 01.02.2026 · 19 (6) · 1332-1344

DOI: 10.14778/3797919.3797938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 08.05.2026. Verfasst von Pranay Mundra und 3 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A two-stage pipeline is commonly used to identify similar text passages in large document corpora: First, a fast approach produces potential matches, which are then examined in detail. Existing approaches for the first step consider only syntactic information and miss semantically similar passages that are syntactically dissimilar. To address this, we define the novel problem of semantic document alignment as a semantic set-similarity problem on k -width windows. For two documents S and T, an exhaustive baseline that evaluates all |S| × |T| window pairs is computationally infeasible since assessing the similarity of a single pair requires O ( k 3 ) time. We propose SeDA, which combines a sophisticated candidate generation technique with a bound cascade to drastically reduce the number of expensive window comparisons. It further exploits overlapping windows to efficiently compute both the bounds and the final similarity scores. Our empirical results on three large document corpora indicate that SeDA prunes over 99% of the window similarity computations, resulting in response-time improvements of 1.5–3 orders of magnitude over the baseline solution and 2–5 orders of magnitude over SBERT. Compared to purely syntactic competitors, SeDA provides competitive runtimes and achieves superior result quality, i.e., near-optimal F1-Score of precision/recall and matching the performance of purely semantic methods such as SBERT.

Zitieren

APA

Mundra, P., Kocher, D., Schäler, M., & Augsten, N. (2026). SeDA: Bridging the Gap between Efficient Syntactic and Precise Semantic Search of Similar Passages in Large Text Corpora. Proceedings of the VLDB Endowment, 19(6), 1332-1344. https://doi.org/10.14778/3797919.3797938

Vancouver

Mundra P, Kocher D, Schäler M, Augsten N. SeDA: Bridging the Gap between Efficient Syntactic and Precise Semantic Search of Similar Passages in Large Text Corpora. Proceedings of the VLDB Endowment. 2026;19(6):1332-1344. doi:10.14778/3797919.3797938

BibTeX
@article{Mundra2026,
  author = {Mundra, Pranay and Kocher, Daniel and Schäler, Martin and Augsten, Nikolaus},
  title = {SeDA: Bridging the Gap between Efficient Syntactic and Precise Semantic Search of Similar Passages in Large Text Corpora},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {1332--1344},
  doi = {10.14778/3797919.3797938}
}
Kostenlos starten →