arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.08460cs.CL
收藏

自然语言逻辑推理的神经统一

Neural Unification for Logic Reasoning over Natural Language

IBM Research / Europe(IBM研究院欧洲分院)

Gabriele Picco, Hoang Thanh Lam, Marco Luca Sbodio, Vanessa Lopez Garcia

摘要:

自动定理证明(ATP)涉及计算机程序的开发,该程序能够表明某些查询(查询)是一组公理(事实和规则)的逻辑结果。存在几个成功的ATP,其中形式化地提供了公理和公理(例如,形式化为一阶逻辑公式)。最近的方法,例如(Clark等人,2020)提出了基于变换器的架构,用于导出以自然语言(英语)表示的给定公理的结构。通过二进制文本分类器验证猜想,其中Transformers模型被训练以预测给定公理的猜想的真值。RuleTaker方法(Clark等人,2020)在准确性和泛化能力方面都取得了令人瞩目的结果,表明当模型使用足够深的查询(至少3个推理步骤)进行训练时,Transformers能够正确回答大多数查询(97.6%),这些查询需要多达5个推理步骤。在这项工作中,我们提出了一种新的架构,即神经统一器,以及一个相对的训练过程,它在泛化方面取得了最先进的结果,表明模仿一个众所周知的推理过程,反向链接,即使模型只在浅层上训练,也可以回答深层查询。该方法在实验中使用不同的基准数据集证明。

英文摘要:

Automated Theorem Proving (ATP) deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules). There exists several successful ATPs where conjectures and axioms are formally provided (e.g. formalised as First Order Logic formulas). Recent approaches, such as (Clark et al., 2020), have proposed transformer-based architectures for deriving conjectures given axioms expressed in natural language (English). The conjecture is verified through a binary text classifier, where the transformers model is trained to predict the truth value of a conjecture given the axioms. The RuleTaker approach of (Clark et al., 2020) achieves appealing results both in terms of accuracy and in the ability to generalize, showing that when the model is trained with deep enough queries (at least 3 inference steps), the transformers are able to correctly answer the majority of queries (97.6%) that require up to 5 inference steps. In this work we propose a new architecture, namely the Neural Unifier, and a relative training procedure, which achieves state-of-the-art results in term of generalisation, showing that mimicking a well-known inference procedure, the backward chaining, it is possible to answer deep queries even when the model is trained only on shallow ones. The approach is demonstrated in experiments using a diverse set of benchmark data.

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。

↑