Matteo Romanello

Sven Najem-Meyer, Frédéric Kaplan, Matteo Romanello. Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025). 2025.

Emanuela Boros, Maud Ehrmann, Matteo Romanello, Sven Najem-Meyer, Frédéric Kaplan. Proceedings of the 8th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2024). 2024.

After decades of massive digitisation, an unprecedented number of historical documents are available in digital format, along with their machine-readable texts. While this represents a major step forward with respect to preservation and accessibility, it also opens up new opportunities in terms of content mining and the next fundamental challenge is to develop appropriate technologies to efficiently search, retrieve, and explore information from this ‘big data of the past’. Among semantic indexing opportunities, the recognition and classification of named entities are in great demand among humanities scholars. Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical, and noisy inputs. In this survey, we present the array of challenges posed by historical documents to NER, inventory existing resources, describe the main approaches deployed so far, and identify key priorities for future developments.

Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain challenging for state-of-the-art models. Their layout considerably varies across editions and their most important regions are mainly defined by semantic rather than graphical characteristics such as position or appearance. This setting calls for a comparison between textual, visual and hybrid approaches. We therefore assess the performances of two transformers (LayoutLMv3 and RoBERTa) and an objection-detection network (YOLOv5). If results show a clear advantage in favor of the latter, we also list several caveats to this finding. In addition to our experiments, we release a dataset of ca. 300 annotated pages sampled from 19th century commentaries.

Citation indexes are by now part of the research infrastructure in use by most scientists: a necessary tool in order to cope with the increasing amounts of scientific literature being published. Commercial citation indexes are designed for the sciences and have uneven coverage and unsatisfactory characteristics for humanities scholars, while no comprehensive citation index is published by a public organisation. We argue that an open citation index for the humanities is desirable, for four reasons: it would greatly improve and accelerate the retrieval of sources, it would offer a way to interlink collections across repositories (such as archives and libraries), it would foster the adoption of metadata standards and best practices by all stakeholders (including publishers) and it would contribute research data to fields such as bibliometrics and science studies. We also suggest that the citation index should be informed by a set of requirements relevant to the humanities. We discuss four such requirements: source coverage must be comprehensive, including books and citations to primary sources; there needs to be chronological depth, as scholarship in the humanities remains relevant over time; the index should be collection driven, leveraging the accumulated thematic collections of specialised research libraries; and it should be rich in context in order to allow for the qualification of each citation, for example, by providing citation excerpts. We detail the fit-for-purpose research infrastructure which can make the Humanities Citation Index a reality. Ultimately, we argue that a citation index for the humanities can be created by humanists, via a collaborative, distributed and open effort.

Citation indexes are by now part of the research infrastructure in use by most scientists: a necessary tool in order to cope with the increasing amounts of scientific literature being published. Commercial citation indexes are designed for the sciences and have uneven coverage and unsatisfactory characteristics for humanities scholars, while no comprehensive citation index is published by a public organization. We argue that an open citation index for the humanities is desirable, for four reasons: it would greatly improve and accelerate the retrieval of sources, it would offer a way to interlink collections across repositories (such as archives and libraries), it would foster the adoption of metadata standards and best practices by all stakeholders (including publishers) and it would contribute research data to fields such as bibliometrics and science studies. We also suggest that the citation index should be informed by a set of requirements relevant to the humanities. We discuss four such requirements: source coverage must be comprehensive, including books and citations to primary sources; there needs to be chronological depth, as scholarship in the humanities remains relevant over time; the index should be collection-driven, leveraging the accumulated thematic collections of specialized research libraries; and it should be rich in context in order to allow for the qualification of each citation, for example by providing citation excerpts. We detail the fit-for-purpose research infrastructure which can make the Humanities Citation Index a reality. Ultimately, we argue that a citation index for the humanities can be created by humanists, via a collaborative, distributed and open effort.