RI: Small: Linguistic Semantics and Discourse from Leaky Distant Supervision

RI：小：来自泄漏远程监督的语言语义和话语

• 批准号: 1618193
• 负责人: Hal Daume
• 金额: $ 40.68万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-08-01 至 2020-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1618193&HistoricalAwards=false
• 关键词: RI; Small; Linguistic; Semantics; Discourse

This project studies novel algorithms for building artificial intelligence (AI) systems that can learn to improve their performance with a human in the loop. Many recent AI successes are driven by large, expensive and difficult-to-collect datasets. This yields systems that are deep, but narrow. The goal of this project is to build technology that will allow AI systems to learn from their interactions with people. The project focuses on key applications related to natural language understanding: building technology to understand the meanings of individual sentences, and integrate those meanings into the meaning of a discourse or dialog. One specific application pursued herein relates to extracting biomedical knowledge from text, which will pave the way to helping biomedical researchers develop novel hypotheses. The work will fund students from underrepresented groups in STEM, and encourage cross-disciplinary education at the graduate and undergraduate levels. Finally, the work will be communicated to the public not just with scientific papers, but internationally through social media and locally through visits to middle schools and high schools.Natural language processing (and other fields of artificial intelligence) have had enormous success by training supervised learning systems on large labeled datasets ("corpora"). Unfortunately, curating such corpora is infeasible except for very specific problems. This happens either because it is too expensive, or it is too difficult to get human labelers to agree on an annotation standard. Instead of relying solely on human labeled data, this project develops algorithms that can learn from human interaction. These systems can continually improve their performance based on downstream performance supervision, often with a human in the loop. This work leverages recent developments on the structured contextual bandits learning framework which provides a theoretically grounded and computationally efficient way in which to develop novel approaches to distant supervision. This resulting learning techniques will push advances in natural language understanding: semantic parsing and discourse interpretation. Furthermore, the underlying imitation learning technology is broadly applicable, including novel applications to recurrent neural network models. To aid adoption by the research community, code and data from this project will be released open source.

该项目研究用于构建人工智能（AI）系统的新算法，这些系统可以学习如何在人类参与的情况下提高其性能。最近的许多人工智能成功都是由大型，昂贵和难以收集的数据集驱动的。这就产生了深而窄的系统。该项目的目标是建立一种技术，使人工智能系统能够从与人的互动中学习。该项目专注于与自然语言理解相关的关键应用：构建技术来理解单个句子的含义，并将这些含义整合到话语或对话的含义中。 本文追求的一个具体应用涉及从文本中提取生物医学知识，这将为帮助生物医学研究人员开发新的假设铺平道路。 这项工作将资助STEM中代表性不足的群体的学生，并鼓励研究生和本科生的跨学科教育。最后，这项工作将不仅通过科学论文向公众传播，还将通过社交媒体向国际传播，并通过访问中学和高中向当地传播。自然语言处理（和人工智能的其他领域）通过在大型标记数据集（“语料库”）上训练监督学习系统取得了巨大的成功。 不幸的是，除了非常具体的问题，管理这样的语料库是不可行的。这种情况的发生要么是因为它太昂贵，要么是因为让人类标签人员同意注释标准太困难。 该项目不是仅仅依赖人类标记的数据，而是开发可以从人类互动中学习的算法。 这些系统可以基于下游性能监督不断提高其性能，通常在循环中有一个人。这项工作利用了最近的发展结构化的上下文土匪学习框架，提供了一个理论基础和计算效率高的方式，开发新的方法来远程监督。由此产生的学习技术将推动自然语言理解的进步：语义分析和话语解释。此外，底层的模仿学习技术具有广泛的适用性，包括对递归神经网络模型的新应用。 为了帮助研究界采用，该项目的代码和数据将开源发布。