Research map / Vision-language and multimodal / Visual question answering
Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
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 |
|---|---|---|---|
| Use CFC instead of Entity-GCN | WikiHop test · WikiHop test | accuracy: 70.6% vs 67.6% | Helped |
| Rerank BiDAF++ candidates with CFC | BiDAF++ · TriviaQA Wikipedia dev, total | EM: 54.0% -> 57.1% | Helped |
| Rerank BiDAF++ candidates with CFC | BiDAF++ · TriviaQA Wikipedia dev, total | F1: 58.7% -> 61.7% | Helped |
| Add the coarse-grain module (ablation) | CFC · WikiHop dev | accuracy: 61.9% -> 66.4% (-4.5%) | Helped |
| Add the fine-grain module (ablation) | CFC · WikiHop dev | accuracy: 63.6% -> 66.4% (-2.8%) | Helped |
| Use self-attention instead of average pooling (ablation) | CFC · WikiHop dev | accuracy: 64.8% -> 66.4% (-1.6%) | Helped |
| Use bidirectional rather than unidirectional GRUs (ablation) | CFC · WikiHop dev | accuracy: 65.4% -> 66.4% (-1.0%) | Helped |
| Use encoder GRUs rather than a projection over word embeddings (ablation) | CFC · WikiHop dev | accuracy: 61.3% -> 66.4% (-5.1%) | Helped |
Closest papers by meaning
- Dynamic Coattention Networks For Question Answering (ICLR 2017 · similarity 0.88)
- DCN+: Mixed Objective And Deep Residual Coattention for Question Answering (ICLR 2018 · similarity 0.88)
- HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering (CVPR 2026 · similarity 0.87)
- TAIA: Large Language Models are Out-of-Distribution Data Learners (NeurIPS 2024 · similarity 0.86)
- DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering (NeurIPS 2025 · similarity 0.85)
- Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models (NeurIPS 2026 · 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.