Probabilistic Graph Reasoning for Natural Proof Generation

2021/07/06 by Changzhi Sun, Sun, Changzhi, Xinbo Zhang +13
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2107.02418

openalex publication_date 2021/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we investigate the problem of reasoning over natural language statements. Prior neural based approaches do not explicitly consider the inter-dependency among answers and their proofs. In this paper, we propose PRobr, a novel approach for joint answer prediction and proof generation. PRobr defines a joint probabilistic distribution over all possible proof graphs and answers via an induced graphical model. We then optimize the model using variational approximation on top of neural textual representation. Experiments on multiple datasets under diverse settings (fully supervised, few-shot and zero-shot evaluation) verify the effectiveness of PRobr, e.g., achieving 10%-30% improvement on QA accuracy in few/zero-shot evaluation. Our codes and models can be found at https://github.com/changzhisun/PRobr/.

Citations

• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic

Related

• Neural Probabilistic Logic Learning for Knowledge Graph Reasoning
• Can Graph Neural Networks Help Logic Reasoning?
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• Scalable Neural-Probabilistic Answer Set Programming
• Computing and Maintaining Provenance of Query Result Probabilities in\n Uncertain Knowledge Graphs