• Publicationsclose
• 2018-2022close
• Open Access close
• Part of book or chapter of book close
• CH close
• English close
• Hyper Article en Ligne close
• Hyper Article en Ligne - Sciences de l'Homme et de la Société close
• Digital Humanities and Cultural Heritage close

We present the HIPE-2022 shared task on named entity processing in multilingual historical documents. Following the success of the first CLEF-HIPE-2020 evaluation lab, this edition confronts systems with the challenges of dealing with more languages, learning domain-specific entities, and adapting to diverse annotation tag sets. HIPE-2022 is part of the ongoing efforts of the natural language processing and digital humanities communities to adapt and develop appropriate technologies to efficiently retrieve and explore information from historical texts. On such material, however, named entity processing techniques face the challenges of domain heterogeneity, input noisiness, dynamics of language, and lack of resources. In this context, the main objective of the evaluation lab is to gain new insights into the transferability of named entity processing approaches across languages, time periods, document types, and annotation tag sets.

Cet article présente les résultats de la campagne de terrain menée au Sénégal oriental en 2017 dans le cadre du programme international « Peuplement humain et paléoenvironnement en Afrique ». Il intègre les résultats de deux projets complémentaires : le projet ANR-FNS CheRCHA, ainsi que le projet FNS Falémé. Le premier vise à reconstituer le cadre chronostratigraphique et les évolutions culturelles au Pléistocène et à l'Holocène ancien et moyen dans la vallée de la Falémé, tandis que le second est ciblé sur les dynamiques techniques des deux derniers millénaires au Sénégal oriental.

International audience; Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a representation is hidden in the neurons and can be made explicit by teaching the model to recognize semantically interpretable attributes that are present in the scene. We call such an intermediate layer a \emph{semantic bottleneck}. Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explicit reasoning behind the CNN decision. In this paper, we look into semantic bottlenecks that capture context: we want attributes to be in groups of a few meaningful elements and participate jointly to the final decision. We use a two-layer semantic bottleneck that gathers attributes into interpretable, sparse groups, allowing them contribute differently to the final output depending on the context. We test our contextual semantic interpretable bottleneck (CSIB) on the task of landscape scenicness estimation and train the semantic interpretable bottleneck using an auxiliary database (SUN Attributes). Our model yields in predictions as accurate as a non-interpretable baseline when applied to a real-world test set of Flickr images, all while providing clear and interpretable explanations for each prediction.