@inproceedings{favaro-etal-2026-lexicographic,
title = "When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?",
author = "Favaro, Manuel and
Guadagnini, Elisa and
Sassolini, Eva and
Biffi, Marco and
Montemagni, Simonetta",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.5/",
doi = "10.63317/4jcig5tk645s",
pages = "49--57",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="favaro-etal-2026-lexicographic">
<titleInfo>
<title>When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Favaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Guadagnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Sassolini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Biffi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">favaro-etal-2026-lexicographic</identifier>
<identifier type="doi">10.63317/4jcig5tk645s</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>49</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?
%A Favaro, Manuel
%A Guadagnini, Elisa
%A Sassolini, Eva
%A Biffi, Marco
%A Montemagni, Simonetta
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F favaro-etal-2026-lexicographic
%X 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.
%R 10.63317/4jcig5tk645s
%U https://aclanthology.org/2026.lt4hala-1.5/
%U https://doi.org/10.63317/4jcig5tk645s
%P 49-57
Markdown (Informal)
[When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?](https://aclanthology.org/2026.lt4hala-1.5/) (Favaro et al., LT4HALA 2026)
ACL