CASCADE: Computational Analysis of Semantic Change Across Different Environments

CASCADE：不同环境下语义变化的计算分析

• 批准号: EP/Y031075/1
• 负责人: Michael Pidd
• 金额: $ 66.43万
• 依托单位: University of Sheffield
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2024
• 资助国家: 英国
• 起止时间: 2024 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FY031075%2F1
• 关键词: CASCADE; Computational; Analysis; Semantic; Change

This network aims to train early-stage researchers to develop and apply innovative methodologies for Computational Analysis of Semantic Change Across Different Environments (CASCADE), i.e. to identify, analyse and interrogate how meaning is expressed in language in diverse contexts, with a shared focus on the impact of time (diachronic text analytics).CASCADE responds to a skills deficit within the academic, public and commercial sectors: the need for people able to retrieve, critically evaluate and make better use of the large volumes of textual data that characterise our contemporary information society (the 'data deluge'). The consortium is a collaboration of some of Europe's world-leading universities and companies from the United Kingdom, Belgium, Finland, Ireland, and Germany.The overall training approach will consist of beneficiaries 'matching up' to host and support 10 individual research projects, in addition to 10 secondments, and reinforced by a programme of network-wide Training Camps and Research Conventions. The key deliverables from each research project, in addition to the anticipated doctoral theses for ESRs 1 to 10, will include 12 co-authored articles for experts, Wikipedia articles for a general audience, and new software and algorithms. The network's unique selling point for potential researchers is its emphasis on computational linguistics and humanities scholarship as skills that bring value and competitive edge to organisations concerned with semantically-aware information retrieval. These organisations might be academic or commercial, involved in early stage R&D (methods development) or early adoption of new methods (methods application).

该网络旨在培训早期研究人员开发和应用跨不同环境语义变化的计算分析（CASCADE）的创新方法，即识别、分析和询问在不同背景下如何用语言表达意义，共同关注时间的影响（历时文本分析）。CASCADE 应对学术、公共和商业部门的技能缺陷：需要人们能够检索、批判性评估和更好地利用大量文本表征我们当代信息社会的文本数据（“数据洪流”）。该联盟由来自英国、比利时、芬兰、爱尔兰和德国的一些欧洲世界领先大学和公司合作组成。总体培训方法将包括受益者“匹配”以主持和支持 10 个单独的研究项目，除了 10 名借调人员外，还通过网络范围内的训练营和研究大会计划予以加强。每个研究项目的主要成果，除了 ESR 1 至 10 的预期博士论文外，还将包括 12 篇为专家共同撰写的文章、为普通受众提供的维基百科文章以及新的软件和算法。该网络对潜在研究人员的独特卖点是它强调计算语言学和人文学术作为为关注语义感知信息检索的组织带来价值和竞争优势的技能。这些组织可能是学术组织或商业组织，参与早期研发（方法开发）或早期采用新方法（方法应用）。