Knowledge Acquisition for Natural Language Understanding

构建能够从文本中阅读、总结和提取信息的健壮系统的一个主要障碍是需要大量的语言知识来处理大量的句法、语义和语用歧义，这些歧义几乎渗透到文本分析的各个方面。本研究旨在解决自然语言处理(NLP)系统的知识工程瓶颈问题。该工作扩展了一个通用的知识获取框架，允许NLP系统使用标准归纳机器学习技术结合标注语料库和稳健的句子分析直接从文本中引导自己的知识库。特别是，该框架正在扩展，以处理词汇和结构歧义解决方面的其他问题，并正在使用宾夕法尼亚州立大学树库数据在一个较大的自然语言处理任务的背景下进行评估。这项工作具有重要的理论意义和实践意义。首先，这项研究将开始确定在什么条件下，机器学习技术可以为自然语言处理系统提供一种成本效益高的知识获取方法，特别是与现有的统计技术相比。其次，这项工作将把目前的系统扩展为一个使用机器学习技术来指导NLP系统开发的综合工具。

A major obstacle to building robust systems that can read, summarize, and extract information from text is the need for large amounts of linguistic knowledge to handle the myriad syntactic, semantic, and pragmatic ambiguities that pervade virtually all aspects of text analysis. The objective of this research is to address this knowledge engineering bottleneck for natural language processing (NLP) systems. The work extends a general knowledge acquisition framework that allows an NLP system to bootstrap its own knowledge bases directly from text using standard inductive machine learning techniques in conjunction with an annotated corpus and robust sentence analysis. In particular, the framework is being extended to handle additional problems in lexical and structural ambiguity resolution and is being evaluated using Penn Treebank data within the context of a larger NLP task. The work is of both theoretical and practical significance. First, the research will begin to determine the conditions under which machine learning techniques can be expected to offer a cost-effective approach to knowledge acquisition for NLP systems, especially in comparison to existing statistical techniques. Second, the work will expand the current system into an integrated tool that uses machine learning techniques to guide NLP system development.