[论文解读] Representing Meaning with a Combination of Logical Form and Vectors.

Islam Beltagy, Stephen Roller+3 more|arXiv (Cornell University)|May 26, 2015

Natural Language Processing Techniques参考文献 88被引用 12

一句话总结

本文提出了一种混合语义框架，通过马尔可夫逻辑网络（MLNs）将基于逻辑的表示与分布式向量模型相结合，用于文本蕴含任务。通过在概率推理中整合逻辑结构与分级语义相似性，该系统在SICK数据集上实现了最先进（SOTA）的性能，同时支持对分布式词汇蕴含方法的评估。

ABSTRACT

NLP tasks differ in the semantic information they require, and at this time no single semantic representation fulfills all requirements. Logic-based representations characterize sentence structure, but do not capture the graded aspect of meaning. Distributional models give graded similarity ratings for words and phrases, but do not adequately capture overall sentence structure. So it has been argued that the two are complementary. In this paper, we adopt a hybrid approach that combines logic-based and distributional semantics through probabilistic logic inference in Markov Logic Networks (MLNs). We focus on textual entailment (RTE), a task that can utilize the strengths of both representations. Our system is three components, 1) parsing and task representation, where input RTE problems are represented in probabilistic logic. This is quite different from representing them in standard first-order logic. 2) knowledge base construction in the form of weighted inference rules from different sources like WordNet, paraphrase collections, and lexical and phrasal distributional rules generated on the fly. We use a variant of Robinson resolution to determine the necessary inference rules. More sources can easily be added by mapping them to logical rules; our system learns a resource-specific weight that counteract scaling differences between resources. 3) inference, where we show how to solve the inference problems efficiently. In this paper we focus on the SICK dataset, and we achieve a state-of-the-art result. Our system handles overall sentence structure and phenomena like negation in the logic, then uses our Robinson resolution variant to query distributional systems about words and short phrases. Therefor, we use our system to evaluate distributional lexical entailment approaches. We also publish the set of rules queried from the SICK dataset, which can be a good resource to evaluate them.

研究动机与目标

• 为解决纯逻辑或分布式语义表示在捕捉句子结构与分级语义方面的局限性。
• 开发一个统一框架，结合逻辑的优势（用于结构与否定）与分布式模型的优势（用于分级相似性），以实现文本蕴含任务。
• 通过将RTE问题编码为概率逻辑并从多样化语言资源构建加权知识库，实现高效且可扩展的推理。
• 创建一个可重用的规则集，用于评估分布式词汇蕴含方法，并与系统一同发布。

提出的方法

• 将输入的文本蕴含问题表示为概率逻辑，而非标准的一阶逻辑，以支持不确定性与概率推理。
• 从WordNet、同义表达语料库以及实时生成的词汇与短语分布式规则等来源，构建加权推理规则知识库。
• 使用罗宾逊归结法的变体，自动推导必要的推理规则，确保在异构语言资源间的兼容性。
• 学习资源特定的权重，以规范化不同数据源之间的缩放差异，提升整合的鲁棒性。
• 在马尔可夫逻辑网络中执行高效推理，将逻辑推理与词汇及短语的分布式相似性得分相结合。
• 通过逻辑谓词查询分布式模型，以评估词汇与短语蕴含，实现对分布式方法的系统性评估。

实验结果

研究问题

• RQ1 结合逻辑与分布式语义的混合系统是否能在文本蕴含任务中超越单一方法？
• RQ2 如何在单一推理框架中有效整合逻辑结构与分级语义相似性？
• RQ3 分布式模型在多大程度上可被系统性地查询，以集成到逻辑推理流程中用于蕴含判断？
• RQ4 能否从SICK等数据集衍生出的规则集，作为评估分布式词汇蕴含方法的可靠基准？

主要发现

• 所提出的系统在SICK数据集上实现了最先进性能，证明了该混合方法的有效性。
• 逻辑结构的整合使得系统能够正确处理复杂现象，如否定与句子级组合性。
• 使用罗宾逊归结法的变体，可从多样化语言资源中自动推导出推理规则。
• 系统成功查询分布式模型以获取词汇与短语的相似性，从而实现对分布式蕴含方法的评估。
• 从SICK数据集发布的推理规则集为未来评估词汇蕴含方法提供了宝贵且可重用的基准。
• 资源特定的权重有效缓解了异构源之间的缩放差异，提升了模型的鲁棒性与性能。