ITR-(NHS)-(dmc)-TREEWORLD: Probabilistic Tree Transducers for Machine Translation and Natural Language Processing

ITR-(NHS)-(dmc)-TREEWORLD：用于机器翻译和自然语言处理的概率树转换器

• 批准号: 0428020
• 负责人: Kevin Knight
• 金额: --
• 依托单位: University of Southern California
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2004
• 资助国家: 美国
• 起止时间: 2004-09-15 至 2009-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0428020&HistoricalAwards=false
• 关键词: ITR; NHS; dmc; TREEWORLD; Probabilistic

Many recent advances in natural language processing (e.g., speech recognition and information extraction) are due to widespread use of finite-state automata. These automata probabilistically transform input strings into output strings, and they can be quickly assembled to tackle new jobs via generic mathematical operations like composition and forward application. However, these automata are a bad fit for many important problems that require syntax-sensitive transformations and large-scale re-ordering (such as language translation and summarization).We are investigating tree automata as an alternative building block for new natural language systems. These automata walk over input trees and produce output trees. Fortunately, there is an extensive mathematical theory associated with these devices. These automata also fit many of the ad hoc models recently proposed in natural language research. However, there are several critical missing pieces: (1) how to design efficient computer science algorithms for generic tree operations, (2) how to design efficient machine learning algorithms for inducing tree automata and probabilities from linguistic data, and (3) how to use automata to accurately model problems in automatic language translation.We expect this research to yield several benefits. Many researchers who currently use finite-state tools will switch to more powerful tree-based automata and obtain more accurate language processing systems. Also, tree automata will enable better understanding of how to model language translation more deeply and accurately, and -- importantly -- in such a way that syntactic and lexical translation knowledge can still be acquired fully automatically by the machine from text corpora.

自然语言处理的许多最新进展（例如，语音识别和信息提取）是由于有限状态自动机的广泛使用。 这些自动机将输入字符串概率地转换为输出字符串，并且它们可以通过合成和向前应用等通用数学运算快速组装以处理新的工作。 然而，这些自动机是一个坏的适合许多重要的问题，需要语法敏感的转换和大规模的重新排序（如语言翻译和摘要）。 这些自动机遍历输入树并产生输出树。 幸运的是，有一个广泛的数学理论与这些设备。 这些自动机也适合许多最近在自然语言研究中提出的特设模型。 然而，有几个关键的缺失部分：（1）如何设计有效的计算机科学算法的通用树操作，（2）如何设计有效的机器学习算法，从语言数据中诱导树自动机和概率，（3）如何使用自动机准确地建模自动语言翻译中的问题。 许多目前使用有限状态工具的研究人员将转向更强大的基于树的自动机，并获得更精确的语言处理系统。 此外，树自动机将使人们能够更好地理解如何更深入、更准确地对语言翻译进行建模，而且重要的是，机器仍然可以从文本语料库中完全自动地获取语法和词汇翻译知识。