学习高效消歧
Learning Efficient Disambiguation
摘要:
本文分析了当前自然语言句法分析,特别是面向数据句法分析(DOP)性能模型的计算特性,指出了它们的一些主要缺陷,并提出了相应的解决方案。它提供的证据表明,概率消歧的各种问题是NP完全的这些性能模型的实例下,它认为,这些模型没有一个占人类语言处理在有限的域,例如,频繁的输入通常比不频繁的处理速度有吸引力的效率属性。本文的中心假设是,这些缺点可以通过将性能模型专门化到有限的领域来消除。本文讨论了“语法和模型专业化”,并提出了一个新的框架,歧义减少专业化(ARS)框架,制定了成功的专业化的必要条件和充分条件。该框架被实例化为具体化算法,并应用于具体化DOP。这些学习算法的新颖之处在于1)它们将假设空间限制为仅包括“安全”模型,2)被表示为在特定模型的大小不超过预定义的最大值的约束下,在给定特定语法的情况下最小化训练树库的熵的约束优化公式,3)它们使得能够以互补的方式将专用模型与原始模型集成。论文提供了初步实现的实验,并比较了产生的专业DOP(SDOP)模型与原始DOP模型,结果令人鼓舞。
英文摘要:
This dissertation analyses the computational properties of current performance-models of natural language parsing, in particular Data Oriented Parsing (DOP), points out some of their major shortcomings and suggests suitable solutions. It provides proofs that various problems of probabilistic disambiguation are NP-Complete under instances of these performance-models, and it argues that none of these models accounts for attractive efficiency properties of human language processing in limited domains, e.g. that frequent inputs are usually processed faster than infrequent ones. The central hypothesis of this dissertation is that these shortcomings can be eliminated by specializing the performance-models to the limited domains. The dissertation addresses "grammar and model specialization" and presents a new framework, the Ambiguity-Reduction Specialization (ARS) framework, that formulates the necessary and sufficient conditions for successful specialization. The framework is instantiated into specialization algorithms and applied to specializing DOP. Novelties of these learning algorithms are 1) they limit the hypotheses-space to include only "safe" models, 2) are expressed as constrained optimization formulae that minimize the entropy of the training tree-bank given the specialized grammar, under the constraint that the size of the specialized model does not exceed a predefined maximum, and 3) they enable integrating the specialized model with the original one in a complementary manner. The dissertation provides experiments with initial implementations and compares the resulting Specialized DOP (SDOP) models to the original DOP models with encouraging results.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。