CLJul 6, 2021

Probabilistic Graph Reasoning for Natural Proof Generation

arXiv:2107.02418v1713 citationsHas Code
AI Analysis

This addresses the challenge of generating natural proofs for question answering, particularly in low-resource settings, though it appears incremental by building on prior neural methods.

The paper tackles the problem of reasoning over natural language statements by proposing PRobr, a novel approach for joint answer prediction and proof generation, which achieves 10%-30% improvement in QA accuracy in few-shot and zero-shot evaluations.

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/.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes