# Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension

arXiv: https://arxiv.org/abs/2005.05806 · HTML: https://mlsanity.com/paper/2005.05806/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 17 of 17)

- [Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks](https://mlsanity.com/paper/2110.04522/) (2021)
- [Fine-Grained Distillation for Long Document Retrieval](https://mlsanity.com/paper/2212.10423/) (2022)
- [A Survey on Deep Learning Event Extraction: Approaches and Applications](https://mlsanity.com/paper/2107.02126/) (2021)
- [ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select](https://mlsanity.com/paper/2210.14427/) (2022)
- [Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network](https://mlsanity.com/paper/2210.05499/) (2022)
- [Constructing Flow Graphs from Procedural Cybersecurity Texts](https://mlsanity.com/paper/2105.14357/) (2021)
- [Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering](https://mlsanity.com/paper/2311.13565/) (2023)
- [What Has Been Enhanced in my Knowledge-Enhanced Language Model?](https://mlsanity.com/paper/2202.00964/) (2022)
- [Lite Unified Modeling for Discriminative Reading Comprehension](https://mlsanity.com/paper/2203.14103/) (2022)
- [GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions](https://mlsanity.com/paper/2206.08441/) (2022)
- [MQENet: A Mesh Quality Evaluation Neural Network Based on Dynamic Graph Attention](https://mlsanity.com/paper/2309.01067/) (2023)
- [Multi-grained Evidence Inference for Multi-choice Reading Comprehension](https://mlsanity.com/paper/2310.18070/) (2023)
- [Metaknowledge Extraction Based on Multi-Modal Documents](https://mlsanity.com/paper/2102.02971/) (2021)
- [VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension](https://mlsanity.com/paper/2105.03229/) (2021)
- [Deep Understanding based Multi-Document Machine Reading Comprehension](https://mlsanity.com/paper/2204.03494/) (2022)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)
- [Exploring and Exploiting Multi-Granularity Representations for Machine Reading Comprehension](https://mlsanity.com/paper/2208.08750/) (2022)

## Abstract (arXiv)

Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragraphs, sentences, and tokens. We utilize graph attention networks to obtain different levels of representations so that they can be learned simultaneously. The long and short answers can be extracted from paragraph-level representation and token-level representation, respectively. In this way, we can model the dependencies between the two-grained answers to provide evidence for each other. We jointly train the two sub-tasks, and our experiments show that our approach significantly outperforms previous systems at both long and short answer criteria.