Advanced natural language processing techniques for smart office assistant

先进的自然语言处理技术，智能办公助手

• 批准号: 564715-2021
• 负责人: Lung, ChungHorng
• 金额: $ 1.75万
• 依托单位: Carleton University
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=722161
• 关键词: Advanced; natural; language; processing; techniques

Natural language processing (NLP) is a rapidly growing field and it has many applications in our daily lives. Due to the rapid advancement of information technology, people in office environments often deal with large volume of information that is stored in various documents and databases. Although document repositories and databases hosted in a centralized server in the office network or the cloud make it possible for employees to access documents, retrieving information from a set of documents is not efficient, especially for non-technical users. These tasks can be simplified by using a smart office assistant that can understand the query made in natural language and can provide the required information. The proposed project is to investigate machine learning techniques for NLP-based smart office assistant. We plan to solicitate requirements from different organizations and evaluate existing machine learning techniques for NLP. In addition, the project is to tailor those techniques for specific needs and develop a prototype for a smart office assistant. Such a product will help Canadian organizations to be more inclusive by facilitating the employment of people with less technical backgrounds. The proposed NLP-based office assistant will also enhance the productivity of employees at businesses and government agencies across Canada due to their ability to quickly retrieve and access documents.

自然语言处理是一个发展迅速的领域，在我们的日常生活中有着广泛的应用。由于信息技术的快速发展，办公环境中的人们经常要处理存储在各种文档和数据库中的大量信息。尽管驻留在办公网络或云中的中央服务器中的文档存储库和数据库使员工能够访问文档，但从一组文档中检索信息的效率很低，对于非技术用户来说尤其如此。使用智能办公助手可以简化这些任务，该助手可以理解以自然语言进行的查询，并可以提供所需的信息。本课题旨在研究基于自然语言处理的智能办公助手的机器学习技术。我们计划关注不同组织的需求，并评估现有的NLP机器学习技术。此外，该项目还将为特定需求量身定做这些技术，并开发一款智能办公助理的原型。这样的产品将通过促进技术背景较少的人的就业，帮助加拿大的组织更具包容性。拟议的基于NLP的办公室助理还将提高加拿大各地企业和政府机构员工的生产力，因为他们能够快速检索和访问文件。