CAREER: Learning Scalable Models for Grounded Semantic Parsing

职业：学习基础语义解析的可扩展模型

• 批准号: 1252835
• 负责人: Luke Zettlemoyer
• 金额: $ 50万
• 依托单位: University of Washington
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-09-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1252835&HistoricalAwards=false
• 关键词: CAREER; Learning; Scalable; Models; Grounded

One core challenge in natural language research is to do robust, wide coverage semantic analysis. Recently, there has been progress towards solving this problem by developing algorithms for learning semantic parsers that map sentences to rich, logical representations of their meaning. State-of-the-art approaches have reached the level where they can, with sufficient training data, be used to learn highly accurate parsers for many different natural languages on a number of benchmark problems. However, the general applicability of this work has been limited by the focus on somewhat idealized conditions, where the application domain is of limited size, sentences are analyzed in isolation, and there is an exclusive focus on database query applications.This CAREER project aims to build a framework for grounded semantic parsing that solves these challenges by reasoning about a sentence's possible meanings given its linguistic and situated context. This type of reasoning is necessary for extending existing learning approaches to fundamentally new applications, such as conversational understanding. However, it is also be crucial for the next generation of semantic parsers that learn from easily gathered data and scale to domains that are several orders of magnitude more complex than previously considered.The project will extend the PI's educational and outreach efforts, including the creation of freely shared online content for introductory and advanced semantics topics. It will also enable new initiatives by the PI to increase diversity in computer science study and research, by supporting efforts to motivate students through early exposure to exciting language understanding problems.

自然语言研究的一项核心挑战是进行稳健、广泛覆盖的语义分析。 最近，通过开发用于学习语义解析器的算法，将句子映射到其含义的丰富的逻辑表示，在解决这个问题方面取得了进展。 最先进的方法已经达到了这样的水平：在足够的训练数据的情况下，它们可以用于在许多基准问题上学习许多不同自然语言的高度准确的解析器。然而，这项工作的普遍适用性受到了对一些理想化条件的关注的限制，其中应用领域的大小有限，句子是孤立分析的，并且只关注数据库查询应用程序。这个职业项目旨在构建一个扎根语义解析框架，通过在给定语言和情境上下文的情况下推理句子的可能含义来解决这些挑战。这种类型的推理对于将现有的学习方法扩展到全新的应用程序（例如会话理解）是必要的。 然而，对于下一代语义解析器来说也至关重要，它可以从轻松收集的数据中学习并扩展到比以前考虑的复杂几个数量级的领域。该项目将扩展 PI 的教育和推广工作，包括创建免费共享的介绍性和高级语义主题的在线内容。它还将使 PI 能够采取新举措，通过支持通过早期接触令人兴奋的语言理解问题来激励学生的努力，从而增加计算机科学研究的多样性。