Assessing the authority of the past in classical commentaries: a computational approach.
PhD project of Sven-Najem Meyer.
Commenting on ancient literature is a long lasting practice among classical scholars. Building on top of this millennial tradition, modern commentaries bear a vividly controverted relation to their forerunners. Commentators are often being accused of relying too heavily on, if not merely plagiarising their most authoritative predecessors. Yet, substantiating the claim somehow remains a probatio diabolica, as it would require a thorough analysis of information transmission in an unreasonably big corpus. This research proposes a computational approach to this question. Using document analysis and natural language processing, I suggest to construe commentaries as sets of interrelated information units. Representing these units in a semantic space such as a graph or a vector space could allow for an automatic, diachronical mapping of information dynamics, thus enabling for a “measure” of the authority of the past.
This PhD is carried out in the framework of the EPFL Doctoral School of Digital Humanities (EDDH) and is part of the SNSF-Ambizione Ajax MultiCommentary project, with Matteo Romanello as Principal Investigator.(Institut d’archéologie et des sciences de l’antiquité, Université de Lausanne).
See also the Ajax project on the SNSF portal and on Github.
Related publications:
Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.
Boosting named entity recognition in domain-specific and low-resource settings
2022-01-13
Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.
Extended Overview of HIPE-2022: Named Entity Recognition and Linking in Multilingual Historical Documents
2022. 13th Conference and Labs of the Evaluation Forum (CLEF 2022), Bologna, Italy, 5-8 Sept 2022. DOI : 10.5281/zenodo.6979577.Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.