2021/09/17 by Gabriele Picco, Picco, Gabriele, Hoang Thanh Lam +5
Computer Science · Mathematics · #Artificial intelligence #Automated reasoning #Automated theorem proving #Axiom #Backward chaining #Computation and Language (cs.CL) #Computer science #Conjecture #Discrete mathematics #FOS: Computer and information sciences #First-order logic #Inference #Inference engine #Logic programming #Machine Learning and Algorithms #Mathematics #Natural Language Processing Techniques #Natural language processing #Programming language #Rule of inference #Theoretical computer science #Topic Modeling #Transformer #Unification #cs.CL
paper · pdf · doi:10.48550/arxiv.2109.08460
published in arXiv (Cornell University), 3939-3950 (Cornell University) · Accepted at EMNLP2021 Findings
arxiv created 2021/09/17 · openalex publication_date 2021/09/17 · arxiv updated 2021/09/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.