# Question Directed Graph Attention Network for Numerical Reasoning over Text

arXiv: https://arxiv.org/abs/2009.07448 · HTML: https://mlsanity.com/paper/2009.07448/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 30 of 35)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [Reasoning Like Program Executors](https://mlsanity.com/paper/2201.11473/) (2022)
- [Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills](https://mlsanity.com/paper/2107.07261/) (2021)
- [Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review](https://mlsanity.com/paper/2202.12205/) (2022)
- [DAGN: Discourse-Aware Graph Network for Logical Reasoning](https://mlsanity.com/paper/2103.14349/) (2021)
- [On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations](https://mlsanity.com/paper/2204.12708/) (2022)
- [Teaching Autoregressive Language Models Complex Tasks By Demonstration](https://mlsanity.com/paper/2109.02102/) (2021)
- [GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond](https://mlsanity.com/paper/2309.16583/) (2023)
- [Towards Fine-grained Causal Reasoning and QA](https://mlsanity.com/paper/2204.07408/) (2022)
- [UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation](https://mlsanity.com/paper/2210.08249/) (2022)
- [NT5?! Training T5 to Perform Numerical Reasoning](https://mlsanity.com/paper/2104.07307/) (2021)
- [DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2211.12668/) (2022)
- [A Neural-Symbolic Approach to Natural Language Understanding](https://mlsanity.com/paper/2203.10557/) (2022)
- [OPERA:Operation-Pivoted Discrete Reasoning over Text](https://mlsanity.com/paper/2204.14166/) (2022)
- [Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems](https://mlsanity.com/paper/2210.05075/) (2022)
- [Complex Reading Comprehension Through Question Decomposition](https://mlsanity.com/paper/2211.03277/) (2022)
- [A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions](https://mlsanity.com/paper/2212.13465/) (2022)
- [Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems](https://mlsanity.com/paper/2211.07455/) (2022)
- [Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations](https://mlsanity.com/paper/2502.11269/) (2025)
- [Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs](https://mlsanity.com/paper/2305.01938/) (2023)
- [Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models](https://mlsanity.com/paper/2205.06733/) (2022)
- [DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text](https://mlsanity.com/paper/2310.12557/) (2023)
- [EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension](https://mlsanity.com/paper/2108.07994/) (2021)
- [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](https://mlsanity.com/paper/2109.02289/) (2021)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Teaching Neural Module Networks to Do Arithmetic](https://mlsanity.com/paper/2210.02703/) (2022)

## Abstract (arXiv)

Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. The code link is at: https://github.com/emnlp2020qdgat/QDGAT