Information delivery vehicule: text summarization and question answering

信息传递载体：文本摘要和问答

• 批准号: 228139-2006
• 负责人: Chali, Yllias
• 金额: $ 1.09万
• 依托单位: University of Lethbridge
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2008
• 资助国家: 加拿大
• 起止时间: 2008-01-01 至 2009-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=393748
• 关键词: Information; delivery; vehicule; text; summarization

In today's information society, we have access to an enormous amount of information. Without appropriate thories, technologies, and tools to obtain the information we need in a clear and useful way, there is an ever increasing risk of information overload (or information fatigue), leading to poor information use and inefficiencies in decision-making. Information retrieval engines, text summarizers, and question answering systems provide complementary functionalities which can be combined to serve a variety of users, ranging from the casual user asking questions of the web to a sophisticated knowledge user. A particular useful complementarity exists between text summarization and question answering systems. From the viewpoint of summarization, question answering is a way to provide the focus for the query-based summarization. From the viewpoint of question answering, summarization is a way of extracting and fusing just the relevant information from a heap of text in answer to a specific question. I am interested in developing techniques for delivering information that is appropriate and relevant to the user, avoiding information overload and assisting informed decision making. This will lead to build up systems that capture the user needs and preferences and generate customized and personalized documents. This research proposal deals with ways in which summarization and question answering technologies can be combined to form truly useful information delivery tools. Based on our previous research experience, the purpose of this project is to design and build up tools at several increasingly sophisticated stages. I am planning to develop theories, technologies and tools to deliver to users information that is relevant and appropriate for the users receiving it, information that they can easily assimilate to enable them to perform their tasks, usually enabling better and more efficient decision-making.

在当今的信息社会，我们可以获得大量的信息。如果没有适当的理论、技术和工具来以清晰、有用的方式获取我们所需的信息，信息过载（或信息疲劳）的风险就会不断增加，导致信息利用率低下和决策效率低下。信息检索引擎、文本摘要器和问答系统提供了互补的功能，这些功能可以结合起来为各种用户提供服务，从偶尔向网络提问的用户到复杂的知识用户。文本摘要和问答系统之间存在一个特别有用的互补性。从文摘的角度来看，问答是为基于查询的文摘提供焦点的一种方式。从问答的角度来看，摘要是一种从一堆文本中提取和融合相关信息以回答特定问题的方法。我感兴趣的是开发技术，提供适当的和相关的信息，以用户，避免信息过载和协助知情决策。这将导致建立系统，捕捉用户的需要和偏好，并生成定制和个性化的文件。本研究计划涉及如何将摘要和问答技术结合起来，形成真正有用的信息传递工具。根据我们以前的研究经验，本项目的目的是在几个日益复杂的阶段设计和建立工具。我正计划开发理论、技术和工具，向用户提供与接收用户相关和适当的信息，这些信息可以很容易地被用户吸收，使他们能够执行任务，通常能够更好和更有效地做出决策。