# Hierarchical Question Answering for Long Documents

arXiv: https://arxiv.org/abs/1611.01839 · HTML: https://mlsanity.com/paper/1611.01839/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2016.

## Built on by (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Large Language Models are Visual Reasoning Coordinators](https://mlsanity.com/paper/2310.15166/) (2023)
- [English Machine Reading Comprehension Datasets: A Survey](https://mlsanity.com/paper/2101.10421/) (2021)
- [Long Context Question Answering via Supervised Contrastive Learning](https://mlsanity.com/paper/2112.08777/) (2021)
- [Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation](https://mlsanity.com/paper/2201.05088/) (2022)
- [DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search](https://mlsanity.com/paper/2602.05014/) (2026)
- [Equivariant Reinforcement Learning for Quadrotor UAV](https://mlsanity.com/paper/2206.01233/) (2022)
- [The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues](https://mlsanity.com/paper/2107.08128/) (2021)
- [It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension](https://mlsanity.com/paper/2406.16779/) (2024)
- [Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction](https://mlsanity.com/paper/2111.09029/) (2021)
- [A Coarse to Fine Question Answering System based on Reinforcement Learning](https://mlsanity.com/paper/2106.00257/) (2021)
- [In Situ Answer Sentence Selection at Web-scale](https://mlsanity.com/paper/2201.05984/) (2022)
- [PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN](https://mlsanity.com/paper/2207.01762/) (2022)
- [MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering](https://mlsanity.com/paper/2310.06436/) (2023)
- [Multi-grained Evidence Inference for Multi-choice Reading Comprehension](https://mlsanity.com/paper/2310.18070/) (2023)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)
- [VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension](https://mlsanity.com/paper/2105.03229/) (2021)
- [Multi Document Reading Comprehension](https://mlsanity.com/paper/2201.01706/) (2022)
- [U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension](https://mlsanity.com/paper/2210.02621/) (2022)
- [Teach model to answer questions after comprehending the document](https://mlsanity.com/paper/2307.08931/) (2023)
- [QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort](https://mlsanity.com/paper/2505.04732/) (2025)

## Abstract (arXiv)

We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neural networks (RNNs), running them over long documents is prohibitively slow because it is difficult to parallelize over sequences. Inspired by how people first skim the document, identify relevant parts, and carefully read these parts to produce an answer, we combine a coarse, fast model for selecting relevant sentences and a more expensive RNN for producing the answer from those sentences. We treat sentence selection as a latent variable trained jointly from the answer only using reinforcement learning. Experiments demonstrate the state of the art performance on a challenging subset of the Wikireading and on a new dataset, while speeding up the model by 3.5x-6.7x.