UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation

TL;DR

UniRPG is a semantic parsing approach that performs unified discrete reasoning over tables and texts for question answering, improving interpretability and scalability without requiring annotated programs.

Contribution

It introduces a neural programmer and symbolic executor framework with distant supervision, enabling effective reasoning over heterogeneous knowledge sources.

Findings

Significantly outperforms state-of-the-art on TAT-QA dataset.

Achieves promising results on DROP dataset without derivation annotations.

Enhances interpretability and scalability in discrete reasoning tasks.

Abstract

Question answering requiring discrete reasoning, e.g., arithmetic computing, comparison, and counting, over knowledge is a challenging task. In this paper, we propose UniRPG, a semantic-parsing-based approach advanced in interpretability and scalability, to perform unified discrete reasoning over heterogeneous knowledge resources, i.e., table and text, as program generation. Concretely, UniRPG consists of a neural programmer and a symbolic program executor, where a program is the composition of a set of pre-defined general atomic and higher-order operations and arguments extracted from table and text. First, the programmer parses a question into a program by generating operations and copying arguments, and then the executor derives answers from table and text based on the program. To alleviate the costly program annotation issue, we design a distant supervision approach for programmer learning, where pseudo programs are automatically constructed without annotated derivations. Extensive experiments on the TAT-QA dataset show that UniRPG achieves tremendous improvements and enhances interpretability and scalability compared with state-of-the-art methods, even without derivation annotation. Moreover, it achieves promising performance on the textual dataset DROP without derivations.