Learning Symbolic Rules for Reasoning in Quasi-Natural Language
arXiv:2111.12038
Abstract
Symbolic reasoning, rule-based symbol manipulation, is a hallmark of human intelligence. However, rule-based systems have had limited success competing with learning-based systems outside formalized domains such as automated theorem proving. We hypothesize that this is due to the manual construction of rules in past attempts. In this work, we ask how we can build a rule-based system that can reason with natural language input but without the manual construction of rules. We propose MetaQNL, a "Quasi-Natural" language that can express both formal logic and natural language sentences, and MetaInduce, a learning algorithm that induces MetaQNL rules from training data consisting of questions and answers, with or without intermediate reasoning steps. Our approach achieves state-of-the-art accuracy on multiple reasoning benchmarks; it learns compact models with much less data and produces not only answers but also checkable proofs. Further, experiments on a real-world morphological analysis benchmark show that it is possible for our method to handle noise and ambiguity. Code will be released at https://github.com/princeton-vl/MetaQNL.
References in corpus (9)
- DeepMath - Deep Sequence Models for Premise Selection
- RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
- Neural Logic Machines
- Generative Language Modeling for Automated Theorem Proving
- Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
- Compositional Generalization by Learning Analytical Expressions
- Learning to Prove Theorems via Interacting with Proof Assistants
- Learning to Reason in Large Theories without Imitation
- Anti-unification in Constraint Logic Programming