# A Deep Cascade Model for Multi-Document Reading Comprehension

arXiv: https://arxiv.org/abs/1811.11374 · HTML: https://mlsanity.com/paper/1811.11374/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 11 of 11)

- [Reason first, then respond: Modular Generation for Knowledge-infused Dialogue](https://mlsanity.com/paper/2111.05204/) (2021)
- [Sequential Cross-Document Coreference Resolution](https://mlsanity.com/paper/2104.08413/) (2021)
- [MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension](https://mlsanity.com/paper/2103.04567/) (2021)
- [Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems](https://mlsanity.com/paper/2107.00368/) (2021)
- [Semantic Sentence Composition Reasoning for Multi-Hop Question Answering](https://mlsanity.com/paper/2203.00160/) (2022)
- [Multi Document Reading Comprehension](https://mlsanity.com/paper/2201.01706/) (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)
- [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)
- [ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations](https://mlsanity.com/paper/2609.39189/) (2026)

## Abstract (arXiv)

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC), while efficiency is obtained from improvements in preliminary retrieval components such as candidate document selection and paragraph ranking. Given the complexity of the real-world multi-document MRC scenario, it is difficult to jointly optimize both in an end-to-end system. To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension. Specifically, irrelevant documents and paragraphs are first filtered out with simple functions for efficiency consideration. Then we jointly train three modules on the remaining texts for better tracking the answer: the document extraction, the paragraph extraction and the answer extraction. Experiment results show that the proposed method outperforms the previous state-of-the-art methods on two large-scale multi-document benchmark datasets, i.e., TriviaQA and DuReader. In addition, our online system can stably serve typical scenarios with millions of daily requests in less than 50ms.