RI: Small: Scalable Algorithms for Learning to Recover Logical Form from Natural Language

RI：小型：用于学习从自然语言恢复逻辑形式的可扩展算法

• 批准号: 1115966
• 负责人: Luke Zettlemoyer
• 金额: $ 30万
• 依托单位: University of Washington
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-08-01 至 2014-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1115966&HistoricalAwards=false
• 关键词: RI; Small; Scalable; Algorithms; Learning

A key aim in Natural Language Processing is to robustly map from natural language sentences to formal representations of their underlying meaning. Recent work has addressed this problem by learning semantic parsers given sentences paired with logical meaning representations. The goal of this project is to develop models and learning algorithms for recovering lexical structure, in the context mapping sentences to logical form. This work is inspired by linguistic theories of the lexicon, but directly motivated by the limitations observed in current, state-of-the-art learning algorithms.The central hypothesis is that a new probabilistic learning approach for lexical generalization can simultaneous achieve the goals of (1) language-independent learning, (2) robustness when analyzing natural, unedited text, and (3) requiring reduced data annotation effort, in a computationally efficient manner that will scale to large learning problems. The approach under development induces a Combinatory Categorial Grammar (CCG), that is modified to replace the traditional, explicit list of lexical items in the lexicon with a distribution over lexical items that allows for significant generalization in the construction of possible syntactic and semantic structures for given input words. Modifying the CCG lexicon in this manner greatly increases the potential to generalize from the available training data without sacrificing the scalability that comes from working within an established grammar formalism for which efficient learning and parsing algorithms have been developed. This work will have impact at the algorithmic level and through applications, including advanced natural language interfaces to databases for non-technical users.

自然语言处理的一个关键目标是将自然语言句子映射到其潜在含义的正式表示。最近的工作已经解决了这个问题，通过学习语义解析器给出的句子与逻辑意义表示配对。该项目的目标是开发用于恢复词汇结构的模型和学习算法，将句子映射到逻辑形式。这项工作的灵感来自于词汇的语言学理论，但直接受到当前最先进的学习算法的局限性的影响。中心假设是，一种新的词汇泛化概率学习方法可以同时实现以下目标：（1）语言独立学习，（2）分析自然，未经编辑的文本时的鲁棒性，（3）需要减少数据注释工作，以一种计算效率高的方式，可以扩展到大的学习问题。开发中的方法诱导组合范畴语法（CCG），修改，以取代传统的，明确的词汇项目列表中的词汇项目的分布，允许显着的泛化在建设中可能的句法和语义结构，为给定的输入单词。以这种方式修改CCG词典极大地增加了从可用训练数据进行概括的可能性，而不会牺牲来自在已建立的语法形式主义内工作的可扩展性，针对该语法形式主义已经开发了有效的学习和解析算法。这项工作将在算法层面和通过应用程序产生影响，包括为非技术用户提供与数据库的高级自然语言接口。