# DAGN: Discourse-Aware Graph Network for Logical Reasoning

arXiv: https://arxiv.org/abs/2103.14349 · HTML: https://mlsanity.com/paper/2103.14349/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning](https://mlsanity.com/paper/2002.04326/) (2020)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- ["Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding](https://mlsanity.com/paper/1909.03065/) (2019)
- [Discourse-Aware Neural Extractive Text Summarization](https://mlsanity.com/paper/1910.14142/) (2019)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)
- [WIQA: A dataset for "What if..." reasoning over procedural text](https://mlsanity.com/paper/1909.04739/) (2019)
- [Dynamically Fused Graph Network for Multi-hop Reasoning](https://mlsanity.com/paper/1905.06933/) (2019)
- [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Question Directed Graph Attention Network for Numerical Reasoning over Text](https://mlsanity.com/paper/2009.07448/) (2020)
- [Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading](https://mlsanity.com/paper/2010.01838/) (2020)
- [Discourse-Aware Neural Rewards for Coherent Text Generation](https://mlsanity.com/paper/1805.03766/) (2018)
- [Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games](https://mlsanity.com/paper/2010.11655/) (2020)
- [BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering](https://mlsanity.com/paper/1904.04969/) (2019)
- [Adversarial Training for Commonsense Inference](https://mlsanity.com/paper/2005.08156/) (2020)
- [Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension](https://mlsanity.com/paper/1908.10721/) (2019)

## Built on by (most cited first, 28 of 28)

- [Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text](https://mlsanity.com/paper/2105.03659/) (2021)
- [Reasoning Like Program Executors](https://mlsanity.com/paper/2201.11473/) (2022)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations](https://mlsanity.com/paper/2209.08207/) (2022)
- [MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning](https://mlsanity.com/paper/2203.00357/) (2022)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack](https://mlsanity.com/paper/2210.15221/) (2022)
- [DisCGen: A Framework for Discourse-Informed Counterspeech Generation](https://mlsanity.com/paper/2311.18147/) (2023)
- [Towards Fine-grained Causal Reasoning and QA](https://mlsanity.com/paper/2204.07408/) (2022)
- [GLoRE: Evaluating Logical Reasoning of Large Language Models](https://mlsanity.com/paper/2310.09107/) (2023)
- [BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles](https://mlsanity.com/paper/2109.11087/) (2021)
- [AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension](https://mlsanity.com/paper/2203.08992/) (2022)
- [Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.00731/) (2022)
- [Exploring Self-supervised Logic-enhanced Training for Large Language Models](https://mlsanity.com/paper/2305.13718/) (2023)
- [Certified Deductive Reasoning with Language Models](https://mlsanity.com/paper/2306.04031/) (2023)
- [CLOMO: Counterfactual Logical Modification with Large Language Models](https://mlsanity.com/paper/2311.17438/) (2023)
- [APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning](https://mlsanity.com/paper/2212.09282/) (2022)
- [Fact-driven Logical Reasoning for Machine Reading Comprehension](https://mlsanity.com/paper/2105.10334/) (2021)
- [MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure](https://mlsanity.com/paper/2210.12487/) (2022)
- [IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning](https://mlsanity.com/paper/2306.15273/) (2023)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text](https://mlsanity.com/paper/2301.02983/) (2023)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension](https://mlsanity.com/paper/2306.12069/) (2023)
- [elBERto: Self-supervised Commonsense Learning for Question Answering](https://mlsanity.com/paper/2203.09424/) (2022)
- [Proposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark](https://mlsanity.com/paper/2309.09602/) (2023)
- [Unsupervised multiple choices question answering via universal corpus](https://mlsanity.com/paper/2402.17333/) (2024)
- [Chaining Event Spans for Temporal Relation Grounding](https://mlsanity.com/paper/2506.14213/) (2025)

## Abstract (arXiv)

Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating passage-level clues for solving logical reasoning QA by using discourse-based information. We propose a discourse-aware graph network (DAGN) that reasons relying on the discourse structure of the texts. The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks. Experiments are conducted on two logical reasoning QA datasets, ReClor and LogiQA, and our proposed DAGN achieves competitive results. The source code is available at https://github.com/Eleanor-H/DAGN.