Research map / Label-efficient and robust learning / Recognition and long-tail
A Multi-View Fusion Neural Network for Answer Selection
Lei Sha, Xiaodong Zhang, Feng Qian, Baobao Chang, Zhifang Sui
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 separate attention views instead of a single summed view (ablation) | MVFNN · WikiQA test | MAP: 0.6882 -> 0.7462 | Improved |
| use separate attention views instead of a single summed view (ablation) | MVFNN · SemEval-2016 CQA | MAP: 0.7780 -> 0.8005 | Improved |
| add co-attention view (ablation) | MVFNN · WikiQA test | MAP: 0.7018 -> 0.7462 | Improved |
| add inquiry main verb view (ablation) | MVFNN · WikiQA test | MAP: 0.7319 -> 0.7462 | Improved |
| add inquiry type view (ablation) | MVFNN · WikiQA test | MAP: 0.7368 -> 0.7462 | Improved |
| add inquiry semantic view (ablation) | MVFNN · WikiQA test | MRR: 0.7576 -> 0.7576 | No clear effect |
| add residual link to simple BiLSTM fusion (ablation) | BiLSTM view fusion · WikiQA test | MAP: 0.7253 -> 0.7312 | Improved |
| use fusion RNN with gated external memory instead of BiLSTM+ResNet (ablation) | MVFNN · WikiQA test | MAP: 0.7312 -> 0.7462 | Improved |
| use fusion RNN with gated external memory instead of BiLSTM+ResNet (ablation) | MVFNN · SemEval-2016 CQA | MAP: 0.7911 -> 0.8005 | Improved |
| use MVFNN instead of Zhang et al. (2017) with extra features | SemEval-2016 CQA · SemEval-2016 CQA | MAP: 0.8014 vs 0.8005 | No clear effect |
Closest papers by meaning
- FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension (ICLR 2018 · similarity 0.87)
- Attentive Interactive Neural Networks for Answer Selection in Community Question Answering (AAAI 2017 · similarity 0.87)
- A Question-Focused Multi-Factor Attention Network for Question Answering (AAAI 2018 · similarity 0.86)
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.86)
- COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data (AAAI 2019 · similarity 0.86)
- Graph-Based Tri-Attention Network for Answer Ranking in CQA (AAAI 2021 · similarity 0.86)
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.
