Paper

Machine Learning Approach to Automatic Thematic Indexing of Voltaire's Complete Works

Researchers apply machine learning to automate thematic indexing of large literary corpora, using Voltaire's works as a test case. The task is framed as multi-label classification, aiming to reduce manual labor in scholarly editions.

0 engagement·1 source·Fri, Jul 10, 2026, 11:54 AM

The paper explores automatic thematic indexing for the Complete Works of Voltaire, specifically the Essai sur les mœurs et l'esprit des nations and the Questions sur l'Encyclopédie. Thematic indexing assigns structured conceptual labels to text sections, traditionally a manual process. The study frames it as a multi-label classification problem, where a model must assign the correct set of themes to each section. This approach could significantly aid scholars in navigating large literary corpora.

Entities

Voltaire(person)Essai sur les mœurs et l'esprit des nations(concept)Questions sur l'Encyclopédie(concept)Automatic Thematic Indexing(concept)

PaperFri, Jul 10, 2026, 12:06 PM

Oxford project evaluates NLP methods for keyword extraction from crowdsourced WWII archive

A University of Oxford project tested three NLP approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—on the Their Finest Hour Online Archive, a crowdsourced WWII digital collection. The study addresses the technical, practical, and ethical challenges of scaling keyword assignment in such collections.

0 engagement·1 source·arxiv

arXiv

PaperFri, Jul 10, 2026, 05:57 PM

Paper challenges text-only pretraining, proposes visual pretraining for language models

A new arXiv paper argues that current language model pretraining discards rich visual information from documents and web pages. The authors propose scalable visual pretraining to incorporate figures, equations, and layouts, aiming to improve language intelligence beyond text-only approaches.