# Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering

arXiv: https://arxiv.org/abs/1811.11934 · HTML: https://mlsanity.com/paper/1811.11934/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

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

- [StructuralLM: Structural Pre-training for Form Understanding](https://mlsanity.com/paper/2105.11210/) (2021)
- [Revisiting Over-smoothing in BERT from the Perspective of Graph](https://mlsanity.com/paper/2202.08625/) (2022)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [SparseBERT: Rethinking the Importance Analysis in Self-attention](https://mlsanity.com/paper/2102.12871/) (2021)
- [Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video](https://mlsanity.com/paper/2203.06667/) (2022)
- [AutoBERT-Zero: Evolving BERT Backbone from Scratch](https://mlsanity.com/paper/2107.07445/) (2021)
- [Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study](https://mlsanity.com/paper/2303.01081/) (2023)
- [Graph Convolutions Enrich the Self-Attention in Transformers!](https://mlsanity.com/paper/2312.04234/) (2023)
- [Iterative Hierarchical Attention for Answering Complex Questions over Long Documents](https://mlsanity.com/paper/2106.00200/) (2021)
- [Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering](https://mlsanity.com/paper/2104.07646/) (2021)
- [HGAN: Hierarchical Graph Alignment Network for Image-Text Retrieval](https://mlsanity.com/paper/2212.08281/) (2022)
- [Context-Aware Interaction Network for Question Matching](https://mlsanity.com/paper/2104.08451/) (2021)
- [A Diffusion-based Method for Multi-turn Compositional Image Generation](https://mlsanity.com/paper/2304.02192/) (2023)
- [FedQAS: Privacy-aware machine reading comprehension with federated learning](https://mlsanity.com/paper/2202.04742/) (2022)
- [CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective](https://mlsanity.com/paper/2205.03540/) (2022)
- [Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus](https://mlsanity.com/paper/2201.11313/) (2022)
- [Enriched BERT Embeddings for Scholarly Publication Classification](https://mlsanity.com/paper/2405.04136/) (2024)
- [Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?](https://mlsanity.com/paper/2608.12332/) (2026)
- [Tracing Origins: Coreference-aware Machine Reading Comprehension](https://mlsanity.com/paper/2110.07961/) (2021)
- [An Automated Question-Answering Framework Based on Evolution Algorithm](https://mlsanity.com/paper/2201.10797/) (2022)
- [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)
- [U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension](https://mlsanity.com/paper/2210.02621/) (2022)
- [QASE Enhanced PLMs: Improved Control in Text Generation for MRC](https://mlsanity.com/paper/2403.04771/) (2024)
- [Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension](https://mlsanity.com/paper/2404.17991/) (2024)
- [GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification](https://mlsanity.com/paper/2404.18942/) (2024)
- [Four Shades of Life Sciences: A Dataset for Disinformation Detection in the Life Sciences](https://mlsanity.com/paper/2507.03488/) (2025)
- [HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning](https://mlsanity.com/paper/2609.16060/) (2026)

## Abstract (arXiv)

This paper describes a novel hierarchical attention network for reading comprehension style question answering, which aims to answer questions for a given narrative paragraph. In the proposed method, attention and fusion are conducted horizontally and vertically across layers at different levels of granularity between question and paragraph. Specifically, it first encode the question and paragraph with fine-grained language embeddings, to better capture the respective representations at semantic level. Then it proposes a multi-granularity fusion approach to fully fuse information from both global and attended representations. Finally, it introduces a hierarchical attention network to focuses on the answer span progressively with multi-level softalignment. Extensive experiments on the large-scale SQuAD and TriviaQA datasets validate the effectiveness of the proposed method. At the time of writing the paper (Jan. 12th 2018), our model achieves the first position on the SQuAD leaderboard for both single and ensemble models. We also achieves state-of-the-art results on TriviaQA, AddSent and AddOne-Sent datasets.