citlab-article-separation-new | Modules used for separating articles

citlab-article-separation-new is a Python library. citlab-article-separation-new has no bugs, it has no vulnerabilities, it has build file available and it has low support. You can download it from GitHub.

This repository is part of the European Union's Horizon 2020 project NewsEye and is mainly used for separating articles in (historical) newspapers and similar documents. The purpose of the NewsEye project is to enable historians and humanities scholars to investigate a great amount of newspaper collections. The newspaper pages are digitized and are available as scanned images. To ensure efficient work, the data processing steps should be as automatic as possible. Generally, newspapers are structured into large numbers of articles. These usually contain a distinct piece of content or describe a certain topic and can mostly be understood without any context. Newspaper articles are crucial entities for historians and humanities scholars who focus on a specific research area and are only interested in articles related to that topic. Additionally, some natural language processing applications, like e.g. topic modeling or event detection, rely on a logical structuring of the underlying text, to be able to extract meaningful information. For this reason it is important to tackle the article separation (AS) task, which tries to form coherent articles, based on previously detected baselines and their respective text. In the following image a schematic overview of the overall AS workflow can be found.