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.

This paper evaluates a hybrid NLP pipeline for supporting the extraction of Roman legal terminology from Jus- tinian’s Digest. Our goal is not to optimize lemmatization in isolation, but to assess whether integrating a Large Language Model (GPT-4o-mini) as a post-processing component improves lemma quality in ways that are critical for downstream glossary construction. Using LatinPipe as a baseline (F1 = 95.05), we test the integration of GPT-4o-mini under three experimental settings (zero-shot with and without prior lemma information, and few-shot prompting) against a manually annotated gold standard of 3,703 sentences and an expert-validated list of legal Latin technical terms. Results show improvement across all settings, with the best performance achieved in the few-shot configuration. Our analysis shows that the hybrid configuration produces selective improvements, significantly more likely for frequent lemmas and verbs forms, suggesting that the LLM layer primarily assists in resolving morphologically ambiguous inflected forms. Although our experimental conditions may not hold in real-world scenarios, we argue that the main contribution of this work is methodological: demonstrating how evaluation can be aligned with downstream terminological goals, rather than proposing a general-purpose solution to domain-specific lemmatization.

This paper presents the retrodigitization project of the Grande Dizionario della Lingua Italiana (GDLI), the largest and most comprehensive historical dictionary of the Italian language. The GDLI’s 23,000 pages — originally designed for human consultation — constitute an exceptional repository of linguistic and cultural-historical information, while posing significant challenges to large-scale digitization and data structuring. The project, still ongoing, will result in the development of a set of interoperable and interlinked resources: (i) a TEI-XML edition of the dictionary text, encoding its complex lexicographic and citation structure; (ii) an annotated corpus of the quoted examples, enabling linguistic and historical research across centuries; and (iii) a database of cited authors and works. Together, these components form a hybrid lexical resource that establishes the foundations for innovative and advanced modes of accessing and exploring the rich and multifaceted content of this historical dictionary.

In this paper we describe some experiments related to a corpus derived from an authoritative historical Italian dictionary, namely the Grande dizionario della lingua italiana (‘Great Dictionary of Italian Language’, in short GDLI). Thanks to the digitization and structuring of this dictionary, we have been able to set up the first nucleus of a diachronic annotated corpus that selects—according to specific criteria, and distinguishing between prose and poetry—some of the quotations that within the entries illustrate the different definitions and sub-definitions. In fact, the GDLI presents a huge collection of quotations covering the entire history of the Italian language and thus ranging from the Middle Ages to the present day. The corpus was enriched with linguistic annotation and used to train and evaluate NLP models for POS tagging and lemmatization, with promising results.

In this paper, we illustrate the integration of an online dialectometric tool, Gabmap, together with an online dialect atlas, the Atlante Lessicale Toscano (ALT-Web). By using a newly created url-based interface to Gabmap, ALT-Web is able to take advantage of the sophisticated dialect visualization and exploration options incorporated in Gabmap. For example, distribution maps showing the distribution in the Tuscan dialect area of a specific dialectal form (selected via the ALT-Web website) are easily obtainable. Furthermore, the complete ALT-Web dataset as well as subsets of the data (selected via the ALT-Web website) can be automatically uploaded and explored in Gabmap. By combining these two online applications, macro- and micro-analyses of dialectal data (respectively offered by Gabmap and ALT-Web) are effectively and dynamically combined.

This article presents the use of NLP techniques (text mining, text analysis) to develop specific tools that allow to create linguistic resources related to the cultural heritage domain. The aim of our approach is to create tools for the building of an online “knowledge network”, automatically extracted from text materials concerning this domain. A particular methodology was experimented by dividing the automatic acquisition of texts, and consequently, the creation of reference corpus in two phases. In the first phase, on-line documents have been extracted from lists of links provided by human experts. All documents extracted from the web by means of automatic spider have been stored in a repository of text materials. On the basis of these documents, automatic parsers create the reference corpus for the cultural heritage domain. Relevant information and semantic concepts are then extracted from this corpus. In a second phase, all these semantically relevant elements (such as proper names, names of institutions, names of places, and other relevant terms) have been used as basis for a new search strategy of text materials from heterogeneous sources. In this case also specialized crawlers (TP-crawler) have been used to work on a bulk of text materials available on line.

In this paper Semantic Press, a tool for the automatic press review, is introduced. It is based on Text Mining technologies and is tailored to meet the needs of the eGovernment and eParticipation communities. First, a general description of the application demands emerging from the eParticipation and eGovernment sectors is offered. Then, an introduction to the framework of the automatic analysis and classification of newspaper content is provided, together with a description of the technologies underlying it.

The paper presents an on-line dialectal resource, ALT-Web, which gives access to the linguistic data of the Atlante Lessicale Toscano, a specially designed linguistic atlas in which lexical data have both a diatopic and diastratic characterisation. The paper focuses on: the dialectal data representation model; the access modalities to the ALT dialectal corpus; ontology-based search.

This paper presents a case study concerning the challenges and requirements posed by next generation language resources, realized as an overall model of open, distributed and collaborative language infrastructure. If a sort of “new paradigm” for language resource sharing is required, we think that the emerging and still evolving technology connected to Grid computing is a very interesting and suitable one for a concrete realization of this vision. Given the current limitations of Grid computing, it is very important to test the new environment on basic language analysis tools, in order to get the feeling of what are the potentialities and possible limitations connected to its use in NLP. For this reason, we have done some experiments on a module of the Linguistic Miner, i.e. the extraction of linguistic patterns from restricted domain corpora. The Grid environment has produced the expected results (reduction of the processing time, huge storage capacity, data redundancy) without any additional cost for the final user.