Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text

By Siyuan Wang, Wanjun Zhong, Duyu Tang, Zhongyu Wei, Zhihao Fan, Daxin Jiang, Ming Zhou, Nan Duan. 2021

90 citations recorded by the source corpus.

Logical reasoning of text requires identifying critical logical structures in the text and performing inference over them. Existing methods for logical reasoning mainly focus on contextual semantics of text while struggling to explicitly model the logical inference process. In this paper, we not only put forward a logic-driven context extension framework but also propose a logic-driven data augmentation algorithm. The former follows a three-step reasoning paradigm, and each step is respectively to extract logical expressions as elementary reasoning units, symbolically infer the implicit expressions following equivalence laws and extend the context to validate the options. The latter augments literally similar but logically different instances and incorporates contrastive learning to better capture logical information, especially logical negative and conditional relationships. We conduct experiments on two benchmark datasets, ReClor and LogiQA. The results show that our method achieves state-of-the-art performance on both datasets, and even surpasses human performance on the ReClor dataset.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Kang Liu
2. Yifei Li
3. Jun Zhao
4. Shizhu He
5. Yixuan Weng
6. Jian-Guang Lou
7. Wanjun Zhong
8. Zeqi Lin

Citations in the corpus

• Reasoning with Transformer-based Models: Deep Learning, but Shallow Reasoning (2021, background): “This does not mean that the tasks would be unsolvable in general: Several studies [Huang et al., 2021, Ouyang et al., 2021, Wang et al., 2021b, Yang et al., 2020, Lourie et al., 2021, Xu et al., 2021] show that the addition of symbolic knowledge (such as date normalization, quasi-logical reasoning,…”
• Large Language Models are Better Reasoners with Self-Verification (2022, background): “More recent work has suggested to adopt pre-training tasks to improve arithmetic reasoning ability (Yoran et al., 2021; Wang et al., 2022).”
• Making Language Models Better Reasoners with Step-Aware Verifier (2022, methodology): “…proposed chain-of-thought reasoning , of which the key insight is the insertion of multi-step reasoning paths before generating the final answers; Wang et al. (2022c) proposed to improve chain-of-thought reasoning via self-consistency , of which the key insight is to conclude the most consistent…”
• On the Advance of Making Language Models Better Reasoners (2022, background): “…systems, including knowledge graphs (Mihaylov and Frank, 2018; Bauer et al., 2018; Kundu et al., 2019; Wang et al., 2019; Lin et al., 2019; Ding et al., 2019; Feng et al., 2020; Wang et al., 2022b), or question taxonomies (Dua et al., 2019; Andor et al., 2019; Hu et al., 2019b; Wang et al., 2022a).”
• From LSAT: The Progress and Challenges of Complex Reasoning (2021, methodology): “They then utilize a neural module to learn continuous vectors for symbolic representations to deal with the uncertainty of data [75, 76, 20].”