Digital libraries oftentimes provide access to historical newspaper archives via keyword-based search. Historical figures and their roles are particularly interesting cognitive access points in historical research. Structuring and clustering news articles would allow more sophisticated access for users to explore such information. However, real-world limitations such as the lack of training data, licensing restrictions and non-English text with OCR errors make the composition of such a system difficult and cost-intensive in practice. In this work we tackle these issues with the showcase of the National Library of the Netherlands by introducing a role-based interface that structures news articles on historical persons. In-depth, component-wise evaluations and interviews with domain experts highlighted our prototype's effectiveness and appropriateness for a real-world digital library collection.

翻译：数字图书馆通常通过基于关键词的搜索提供对历史报纸档案的访问。历史人物及其角色是历史研究中尤为引人关注的认知切入点。对新闻文章进行结构化与聚类，可使用户以更复杂的方式探索此类信息。然而，现实世界的限制（如训练数据不足、许可限制以及含有光学字符识别错误的非英语文本）使得此类系统的构建在实际中既困难又成本高昂。本研究以荷兰国家图书馆为例，通过引入一种基于角色的界面对历史人物相关新闻文章进行结构化，以应对上述问题。深入的组件评估及与领域专家的访谈表明，我们的原型在真实数字图书馆馆藏中具有有效性与适用性。