# UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation arXiv: https://arxiv.org/abs/2210.08249 ยท HTML: https://mlsanity.com/paper/2210.08249/ ## Key facts - Cited by 13 papers in the map (data through 14 Oct 2026). - Builds on 26 of its 38 references that are in the map. - First posted on arXiv 15 Oct 2022. ## Builds on (most cited first, 26 of 26) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019) - [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017) - [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019) - [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021) - [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015) - [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020) - [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021) - [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020) - [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021) - [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016) - [Open Question Answering over Tables and Text](https://mlsanity.com/paper/2010.10439/) (2020) - [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020) - [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021) - [Towards Robustness of Text-to-SQL Models against Synonym Substitution](https://mlsanity.com/paper/2106.01065/) (2021) - [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019) - [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019) - [Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension](https://mlsanity.com/paper/1909.00109/) (2019) - [A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning](https://mlsanity.com/paper/1908.05514/) (2019) - [S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers](https://mlsanity.com/paper/2203.06958/) (2022) - [Question Directed Graph Attention Network for Numerical Reasoning over Text](https://mlsanity.com/paper/2009.07448/) (2020) - [Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder](https://mlsanity.com/paper/2209.07692/) (2022) - [Table-based Fact Verification with Self-adaptive Mixture of Experts](https://mlsanity.com/paper/2204.08753/) (2022) - [OPERA:Operation-Pivoted Discrete Reasoning over Text](https://mlsanity.com/paper/2204.14166/) (2022) - [EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension](https://mlsanity.com/paper/2108.07994/) (2021) - [HCqa: Hybrid and Complex Question Answering on Textual Corpus and Knowledge Graph](https://mlsanity.com/paper/1811.10986/) (2018) ## Built on by (most cited first, 13 of 13) - [TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2401.13223/) (2024) - [S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering](https://mlsanity.com/paper/2305.11725/) (2023) - [Enhancing Financial Question Answering with a Multi-Agent Reflection Framework](https://mlsanity.com/paper/2410.21741/) (2024) - [Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question](https://mlsanity.com/paper/2305.03458/) (2023) - [MuGER2: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering](https://mlsanity.com/paper/2210.10350/) (2022) - [SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA](https://mlsanity.com/paper/2310.06675/) (2023) - [A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions](https://mlsanity.com/paper/2212.13465/) (2022) - [Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs](https://mlsanity.com/paper/2305.01938/) (2023) - [HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering](https://mlsanity.com/paper/2309.12669/) (2023) - [HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge](https://mlsanity.com/paper/2308.11257/) (2023) - [Training Table Question Answering via SQL Query Decomposition](https://mlsanity.com/paper/2402.13288/) (2024) - [CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.03489/) (2025) - [FINCH: Financial Intelligence using Natural language for Contextualized SQL Handling](https://mlsanity.com/paper/2510.01887/) (2025) ## Abstract (arXiv) 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.