[论文解读] Learning Unification-Based Natural Language Grammars

Miles Osborne|arXiv (Cornell University)|Feb 3, 1995

Natural Language Processing Techniques参考文献 89被引用 3

一句话总结

本文提出一种混合学习方法，结合数据驱动与基于模型的方法，以纠正基于统一的自然语言语法中的欠覆盖问题。通过将口语英语语料库的数据与语言学模型相结合，该系统减少了欠覆盖和过覆盖，生成的语法在覆盖范围和正确性方面均有提升，能够产生语言上合理的解析结果。

ABSTRACT

When parsing unrestricted language, wide-covering grammars often undergenerate. Undergeneration can be tackled either by sentence correction, or by grammar correction. This thesis concentrates upon automatic grammar correction (or machine learning of grammar) as a solution to the problem of undergeneration. Broadly speaking, grammar correction approaches can be classified as being either {\it data-driven}, or {\it model-based}. Data-driven learners use data-intensive methods to acquire grammar. They typically use grammar formalisms unsuited to the needs of practical text processing and cannot guarantee that the resulting grammar is adequate for subsequent semantic interpretation. That is, data-driven learners acquire grammars that generate strings that humans would judge to be grammatically ill-formed (they {\it overgenerate}) and fail to assign linguistically plausible parses. Model-based learners are knowledge-intensive and are reliant for success upon the completeness of a {\it model of grammaticality}. But in practice, the model will be incomplete. Given that in this thesis we deal with undergeneration by learning, we hypothesise that the combined use of data-driven and model-based learning would allow data-driven learning to compensate for model-based learning's incompleteness, whilst model-based learning would compensate for data-driven learning's unsoundness. We describe a system that we have used to test the hypothesis empirically. The system combines data-driven and model-based learning to acquire unification-based grammars that are more suitable for practical text parsing. Using the Spoken English Corpus as data, and by quantitatively measuring undergeneration, overgeneration and parse plausibility, we show that this hypothesis is correct.

研究动机与目标

• 解决广泛覆盖语法中的欠覆盖问题，即语法规则无法解析合法句子。
• 克服纯数据驱动学习者的局限性，后者常导致生成语法错误的句子。
• 通过数据填补语言知识的不完整，缓解基于模型学习者的不完整性。
• 开发一种系统，平衡数据驱动学习（以提升覆盖范围）与基于模型学习（以确保正确性）。
• 构建一个适用于实际文本处理的语法学习框架，实现可靠的语义解析。

提出的方法

• 使用口语英语语料库进行数据驱动学习，以识别缺失的句法模式。
• 应用基于模型的学习方法，利用预设的语言学模型来约束语法规则。
• 采用基于统一的形式化方法表示语法约束与特征结构。
• 在混合学习架构中结合两种方法，使数据纠正模型的缺陷，同时模型过滤噪声数据。
• 采用定量指标评估欠覆盖、过覆盖以及解析的合理性。
• 通过解析结果反馈与语言学合理性判断，迭代优化语法。

实验结果

研究问题

• RQ1 结合数据驱动与基于模型的学习方法，能否减少基于统一语法的欠覆盖问题？
• RQ2 与纯数据驱动方法相比，该混合方法是否能有效防止过覆盖？
• RQ3 基于模型的组件在多大程度上提升了解析的语言学合理性？
• RQ4 该系统在实现广泛覆盖与语法正确性之间有多高效？
• RQ5 能否使用真实世界语料库数据与定量指标对系统进行实证验证？

主要发现

• 与仅使用基于模型学习相比，该混合系统显著减少了欠覆盖。
• 由于基于模型的组件过滤了数据驱动学习识别出的不合法结构，过覆盖被最小化。
• 解析合理性得到改善，因为生成的语法能对更广泛范围的句子产生语言上可接受的分析。
• 与单独使用数据驱动或基于模型的方法相比，该系统在覆盖范围与正确性之间实现了更优的平衡。
• 使用口语英语语料库的定量评估证实，该混合方法在所有关键指标上均优于基线方法。
• 该方法在需要广泛覆盖与语言准确性结合的实际文本解析系统中具有可行性。