Collaborative Research: CompCog: Broad-coverage probabilistic models of communication in context

协作研究：CompCog：上下文中通信的广泛覆盖概率模型

• 批准号: 1829350
• 负责人: Roger Levy
• 金额: $ 11.53万
• 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: 2017
• 资助国家: 美国
• 起止时间: 2017-11-01 至 2019-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1829350&HistoricalAwards=false
• 关键词: Collaborative; Research; CompCog; Broad; coverage

People often mean more than they say. To take an example, imagine Adam says "I could use a cup of coffee" and Bob responds by saying "There's a place called Joe's around the corner." We understand this as a coherent exchange even though Adam's utterance wasn't phrased overtly as a question and Bob didn't explicitly say that Joe's sells coffee. Extracting this rich additional meaning requires us to consider sentences in light of both the context they are used in and the cooperative motivations of Adam and Bob in using language (what are called "pragmatic inferences"). This project is devoted to constructing formal models of these pragmatic inferences. Modeling pragmatic inference is a major scientific challenge in the study of language and the human mind and a key to the future development of autonomous intelligent systems that can communicate with humans using natural language. Machines that can do robust language understanding in context will pave the way for societally beneficial technological applications such as adaptive intelligent tutoring and assistive technologies. The technical core of the project involves developing and extending models of pragmatic reasoning, drawing on ideas and insights from decision theory, probabilistic models of cognition, bounded rationality, and linguistics. In particular, the work extends the recently developed family of "rational speech act" (RSA) models, which provides a set of formal tools that can be used to address basic challenges in psycholinguistics concerning how major principles of pragmatic inference fall out of simple assumptions about cooperativity and shared context among conversation participants. This enterprise has the potential to fill a major open theoretical gap in our scientific understanding of human language and social cognition. Project work includes developing computational Bayesian models of semantic composition and pragmatic inference and testing those models using controlled psycholinguistic experiments. The work will also yield new models and publicly available datasets and will contribute to interdisciplinary connections by creating and reinforcing links between linguistics, psychology, and computer science.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人们的意思往往比他们所说的要多。举个例子，假设亚当说“我需要一杯咖啡”，鲍勃回答说“拐角处有一个叫乔的地方”。我们将其理解为连贯的交流，尽管 Adam 的话语并未公开地表达为问题，并且 Bob 也没有明确表示 Joe's 卖咖啡。提取这种丰富的附加含义需要我们根据句子所使用的上下文以及 Adam 和 Bob 在使用语言时的合作动机（所谓的“语用推理”）来考虑句子。该项目致力于构建这些实用推论的正式模型。语用推理建模是语言和人类思维研究中的一项重大科学挑战，也是未来发展能够使用自然语言与人类交流的自主智能系统的关键。能够在上下文中进行强大的语言理解的机器将为适应性智能辅导和辅助技术等对社会有益的技术应用铺平道路。该项目的技术核心涉及开发和扩展实用推理模型，借鉴决策理论、认知概率模型、有限理性和语言学的思想和见解。 特别是，这项工作扩展了最近开发的“理性言语行为”（RSA）模型家族，该模型提供了一套正式工具，可用于解决心理语言学中的基本挑战，即语用推理的主要原则如何脱离简单的假设关于对话参与者之间的协作和共享上下文。这项事业有潜力填补我们对人类语言和社会认知的科学理解中的一个重大开放理论空白。项目工作包括开发语义构成和语用推理的计算贝叶斯模型，并使用受控心理语言学实验测试这些模型。 这项工作还将产生新的模型和公开可用的数据集，并将通过创建和加强语言学、心理学和计算机科学之间的联系，为跨学科联系做出贡献。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力评估进行评估，被认为值得支持。优点和更广泛的影响审查标准。