Research map / Large language models / Retrieval and knowledge
A Deep Cascade Model for Multi-Document Reading Comprehension
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add manual features (ablation) | Deep Cascade Model · DuReader development | BLEU-4: 49.8 -> 50.8 | Helped |
| add manual features (ablation) | Deep Cascade Model · TriviaQA development | F1: 73.0 -> 73.8 | Helped |
| add the multi-document shared LSTM (ablation) | Deep Cascade Model · DuReader development | BLEU-4: 48.7 -> 50.8 | Helped |
| add the multi-document shared LSTM (ablation) | Deep Cascade Model · TriviaQA development | F1: 70.5 -> 73.8 | Helped |
| add cascade document and paragraph ranking (ablation) | Deep Cascade Model · DuReader development | BLEU-4: 47.0 -> 50.8 | Helped |
| add cascade document and paragraph ranking (ablation) | Deep Cascade Model · TriviaQA development | F1: 71.1 -> 73.8 | Helped |
| add multi-task learning for document, paragraph, and answer extraction (ablation) | Deep Cascade Model · DuReader development | BLEU-4: 48.5 -> 50.8 | Helped |
| add multi-task learning for document, paragraph, and answer extraction (ablation) | Deep Cascade Model · TriviaQA development | F1: 70.9 -> 73.8 | Helped |
| add document extraction as an auxiliary task (ablation) | Answer Span Extraction · DuReader development | BLEU-4: 48.5 -> 49.7 | Helped |
| add paragraph extraction as an auxiliary task (ablation) | Answer Span Extraction · DuReader development | BLEU-4: 48.5 -> 49.2 | Helped |
| add both document and paragraph extraction as auxiliary tasks (ablation) | Answer Span Extraction · DuReader development | BLEU-4: 48.5 -> 50.8 | Helped |
| use 4 documents and 2 paragraphs per document rather than fewer candidates (ablation) | Deep Cascade Model · DuReader development | BLEU-4: 32.1 -> 50.8 | Helped |
Closest papers by meaning
- Multi-Mention Learning for Reading Comprehension with Neural Cascades (ICLR 2018 · similarity 0.89)
- A Unified Model for Document-Based Question Answering Based on Human-Like Reading Strategy (AAAI 2018 · similarity 0.88)
- End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering (NeurIPS 2021 · similarity 0.88)
- Select, Answer and Explain: Interpretable Multi-Hop Reading Comprehension over Multiple Documents (AAAI 2020 · similarity 0.87)
- DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering (NeurIPS 2025 · similarity 0.87)
- NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.