EMCODIST: A Context-based Search Tool for Email Archives
EMCODIST: A Context-based Search Tool for Email Archives
复制标题
DOI：
10.1109/bigdata52589.2021.9671832
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Santhilata Kuppili Venkata;S. Decker;D. Kirsch;Adam Nix
中科院分区：
文献类型：
--
作者：
Santhilata Kuppili Venkata;S. Decker;D. Kirsch;Adam Nix
保存电子邮件对未来发现替代历史来源提出了特别的挑战。电子邮件代表个人之间的通信，当被视为组织范围的集合时，包含大量信息。现有的搜索工具可以提取命名实体和关键字搜索，但在跨多个托管人提取模式和上下文信息时效果较差。为了解决这个问题，我们提出了EMCODIST，一个发现工具，用于使用基于注意力的自然语言处理（NLP）模型在电子邮件中搜索上下文信息。EMCODIST旨在引导最终用户个性化他们的搜索概念。在本文中，我们解释的定义的“上下文”的电子邮件，这也是适合面向对象的计算建模。该工具是根据提取的电子邮件的相关性进行评估。
Preservation of emails poses particular challenges to future discovery as alternative historical sources. Emails represent communications between individuals and contain a wealth of information when viewed as an organisation-wide collection. Existing search tools can extract named entities and keyword searches but are less effective when it comes to extracting patterns and contextual information across multiple custodians. To address this, we present EMCODIST, a discovery tool for searching the contextual information across emails using attention-based models of Natural Language Processing (NLP). The EMCODIST aims to steer end-users to personalise their searches towards a concept. In this paper, we explain the definition of the ‘context’ for emails which is also suitable for object-oriented computational modelling. The tool is evaluated based on the relevancy of the emails extracted.