Daidalos Project - Development of an Infrastructure for the Use of Natural Language Processing for Researchers in Classical Philology

Daidalos 项目 - 为古典语言学研究人员开发使用自然语言处理的基础设施

• 批准号: 518919950
• 负责人: Dr. Andrea Beyer
• 金额: --
• 依托单位: Computer- und Medienservice (Rechenzentrum)
• 依托单位国家: 德国
• 项目类别: Research data and software (Scientific Library Services and Information Systems)
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/518919950?language=en
• 关键词: Daidalos; Project; Development; Infrastructure; Use

The Daidalos project aims to develop an infrastructure with the help of which Latin and Greek texts can be analysed by the researchers themselves using Natural Language Processing methods, e.g. part-of-speech tagging, named entity recognition, sentiment analysis, topic modelling. To this end, these methods are made available to researchers in such a way that they can apply them to an individually compiled research corpus. Thus, the Daidalos project focuses on providing an easily accessible platform of diverse digital research methods that support both linguistic-historical, e.g. the contextualisation of a word over time, and literary-scientific research projects, e.g. the analysis of author-specific discourse structures. In order to be able to support the widest possible range of digital research methods, language-specific solutions are reused and existing solutions from modern languages are adapted. In workshops and through the preparation of method-specific learning modules, researchers, teachers and students of Classical Philology will be introduced to working with Natural Language Processing in general and with the software to be developed in particular, in order to enable new perspectives on innovative or already existing research questions in Classics on the basis of the data-driven analyses. Through the integration of this target group, the planned workshops in particular support the supraregional dissemination and sustainable acceptance of the infrastructure, in addition to the development of professional competence (digital literacy).

Daidalos项目旨在开发一个基础设施，在此基础设施的帮助下，研究人员可以使用自然语言处理方法分析拉丁文和希腊文文本，例如词性标记，命名实体识别，情感分析，主题建模。为此，这些方法提供给研究人员，他们可以将其应用到一个单独编译的研究语料库。因此，Daidalos项目的重点是提供一个易于访问的平台，提供各种数字研究方法，支持语言历史，例如一个词随着时间的推移的语境化，以及文学科学研究项目，例如对作者特定话语结构的分析。为了能够支持尽可能广泛的数字研究方法，语言特定的解决方案被重复使用，现代语言的现有解决方案被改编。在研讨会上，并通过特定方法的学习模块的准备，研究人员，教师和古典文献学的学生将被介绍到一般与自然语言处理，特别是与软件开发，以使创新的新观点或已经存在的研究问题在经典的基础上数据驱动的分析。通过对这一目标群体的整合，计划中的讲习班特别支持跨区域传播和基础设施的可持续接受，以及专业能力的发展（数字扫盲）。