SGER: Reconstructing the Tower of Babel: Cross-lingual Language Learning

SGER：重建巴别塔：跨语言语言学习

• 批准号: 0835445
• 负责人: Regina Barzilay
• 金额: --
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2008
• 资助国家: 美国
• 起止时间: 2008-06-01 至 2009-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0835445&HistoricalAwards=false
• 关键词: SGER; Reconstructing; Tower; Babel; Cross

SGER: Reconstructing the Tower of Babel: Cross-lingual Language LearningToday, there are more than 6,000 living languages in the world. It is widely agreed among linguists that human languages share substantial similarity at all the levels of linguistic structure. The study of this connection has made possible major discoveries about human communication: it has revealed the evolutionary history of languages, facilitated the reconstruction of proto-languages and led to understanding language universals. The goal of cross-lingual learning is to capitalize on the deep connection between human languages to improve automatic language processing. This exploratory research effort focuses on the use of hierarchical Bayesian models that jointly induce linguistic structure for each language and at the same time identify cross-lingual correspondence patterns. The cross-lingual learning is studied in several tasks ranging from morphological to syntactic analysis.The expected benefits of this approach are three fold. First, the performance of cross-lingual learning could yield substantial improvement over state-of-the-art unsupervised approaches across a range of tasks. Second, cross-lingual learning is applicable to hundreds of human languages with no annotated resources which are currently out of reach for existing text processing methods. Finally, tools developed in the course of this project will provide powerful comparative analysis methods for researchers in fields such as linguistics, history, and anthropology.

SGER：重建巴别塔：跨语言学习今天，世界上有超过6000种活的语言。语言学家普遍认为，人类语言在语言结构的各个层次上都有很大的相似性。对这种联系的研究使人类交流的重大发现成为可能：它揭示了语言的进化史，促进了原始语言的重建，并导致了对语言共性的理解。跨语言学习的目标是利用人类语言之间的深层联系来提高自动语言处理。这一探索性研究的重点是使用分层贝叶斯模型，共同归纳每种语言的语言结构，同时识别跨语言对应模式。跨语言学习从词形分析到句法分析等方面进行了研究。这种方法的预期好处有三个方面。首先，跨语言学习的表现可以在一系列任务中比最先进的无监督方法产生实质性的改进。第二，跨语言学习适用于数百种没有注释资源的人类语言，这是目前现有文本处理方法无法达到的。最后，在这个项目过程中开发的工具将为语言学、历史和人类学等领域的研究人员提供强大的比较分析方法。