When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?

Manuel Favaro, Elisa Guadagnini, Eva Sassolini, Marco Biffi, Simonetta Montemagni


Abstract
Historical dictionaries are increasingly reused as sources for diachronic language corpora. In this context, lexicographic quotations represent a valuable yet challenging type of data, as they are both editorially curated and diachronically representative. A major issue in their computational reuse is the presence of duplicate and near-duplicate quotations. This paper addresses quotation deduplication in corpora derived from lexicographic resources. We introduce QRD (Quotation Reuse Detection), a multi-stage pipeline designed to identify, compare, and cluster quotations based on graded similarity rather than binary matching. The approach combines string-based similarity measures, iterative threshold analysis, and clustering, enabling both quantitative and qualitative investigation of quotation reuse. Our results show that deduplication in this context cannot be reduced to the automatic elimination of redundant data. The variability observed in the quotations - ranging from OCR-related noise to substantial editorial variation - reflects both technical and structural factors and calls for a more nuanced approach. QRD supports the identification of OCR-related errors and reveals patterns of textual reuse underlying the compilation of the dictionary. We argue that quotation deduplication should be conceived primarily as a task of identification and clustering. This perspective reframes deduplication from a data-cleaning operation into an analytical methodology for historically and editorially curated textual resources.
Anthology ID:
2026.lt4hala-1.5
Volume:
Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Rachele Sprugnoli, Marco Passarotti
Venues:
LT4HALA | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
49–57
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-lt4hala-05
DOI:
10.63317/4jcig5tk645s
Bibkey:
Cite (ACL):
Manuel Favaro, Elisa Guadagnini, Eva Sassolini, Marco Biffi, and Simonetta Montemagni. 2026. When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 49–57, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate? (Favaro et al., LT4HALA 2026)
Copy Citation: