D4.1 – Natural Language Processing Tools for Cultural Heritage Texts

This document describes the Natural Language Processing (NLP) models used for the automatic processing of textual sources for InTaVia. This work package includes models for Dutch, English, Finnish, German and Slovenian, which focus on the automatic recognition of names, places, events and time expressions in the cultural heritage text domain. The automatic recognition of these entities usually involves several lower-level linguistic annotations, which are also provided by the tools described in this document. This deliverable also focuses on providing a thorough description of the current NLP tools available for the different languages used in the consortium and lay the groundwork for future improvement and standardisation of NLP pipelines.

This deliverable is currently classified as confidential and is not available for download.