Exploiting Context in Multilingual Understanding and Generation

在多语言理解和生成中利用上下文

• 批准号: FT190100039
• 负责人: Prof Gholamreza Haffari
• 金额: $ 60.21万
• 依托单位: Monash University
• 依托单位国家: 澳大利亚
• 项目类别: ARC Future Fellowships
• 财政年份: 2020
• 资助国家: 澳大利亚
• 起止时间: 2020-11-20 至 2025-02-02
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/FT190100039
• 关键词: Exploiting; Context; Multilingual; Understanding; Generation

Automatic translation technologies produce incoherent and incorrect outputs in critical areas, such as health, finance, and law. This is due to translating sentences independently, without regard to the global extra-sentential context and rich linguistic structures inherent in the wider document context. This project aims to exploit global linguistic structures, capitalising on recent advances in deep neural networks, in order to generate coherent and faithful text. Expected outcome include next-generation computational technologies for language understanding and generation. This should significantly benefit document-based language technologies and increase their applications in a range of cultural, industrial, and health settings.

自动翻译技术在卫生、金融和法律等关键领域产生不连贯和不正确的输出。这是因为独立翻译句子，而不考虑全球的句外语境和更广泛的文件语境中固有的丰富的语言结构。该项目旨在利用全球语言结构，利用深度神经网络的最新进展，以产生连贯和忠实的文本。预期成果包括用于语言理解和生成的下一代计算技术。这将大大有利于基于文档的语言技术，并增加它们在文化、工业和卫生环境中的应用。