Research map / Vision-language and multimodal / Visual question answering
Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching
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 multi-scale matching to word-to-word matching (ablation) | Discriminator without adversarial training · SemEval 2017 | MAP: 14.67 -> 14.80 | Helped |
| Add multi-scale matching to word-to-word matching (ablation) | Discriminator with adversarial training · SemEval 2017 | MAP: 17.25 -> 17.91 | Helped |
| Add adversarial training with generated challenging negatives (ablation) | Single-scale discriminator · SemEval 2017 | MAP: 14.67 -> 17.25 | Helped |
| Add adversarial training with generated challenging negatives (ablation) | Multi-scale discriminator · SemEval 2017 | MAP: 14.80 -> 17.91 | Helped |
| Add multi-scale matching to word-to-word matching (ablation) | Discriminator without adversarial training · SemEval 2016 | MAP: 48.11 -> 49.25 | Helped |
| Add multi-scale matching to word-to-word matching (ablation) | Discriminator with adversarial training · SemEval 2016 | MAP: 52.09 -> 53.38 | Helped |
| Add adversarial training with generated challenging negatives (ablation) | Single-scale discriminator · SemEval 2016 | MAP: 48.11 -> 52.09 | Helped |
| Add adversarial training with generated challenging negatives (ablation) | Multi-scale discriminator · SemEval 2016 | MAP: 49.25 -> 53.38 | Helped |
Closest papers by meaning
- Attentive User-Engaged Adversarial Neural Network for Community Question Answering (AAAI 2020 · similarity 0.89)
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.87)
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (AAAI 2017 · similarity 0.87)
- Community-Based Question Answering via Heterogeneous Social Network Learning (AAAI 2016 · similarity 0.86)
- Attentive Interactive Neural Networks for Answer Selection in Community Question Answering (AAAI 2017 · similarity 0.86)
- VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models (AAAI 2024 · 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.