UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation
This addresses the problem of interpretable and scalable question answering for tasks requiring discrete reasoning, such as arithmetic and comparison, but it is incremental as it builds on existing semantic-parsing methods with a novel distant supervision technique.
The paper tackles the challenge of discrete reasoning over heterogeneous knowledge sources like tables and text by proposing UniRPG, a semantic-parsing-based approach that generates programs to answer questions, achieving significant improvements on the TAT-QA dataset and promising results on DROP without requiring annotated derivations.
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.