AI Paper Atlas

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

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 30 citations (OpenAlex)

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 changedWhereMeasuredEffect
use separate attention views instead of a single summed view (ablation)MVFNN · WikiQA testMAP: 0.6882 -> 0.7462Improved
use separate attention views instead of a single summed view (ablation)MVFNN · SemEval-2016 CQAMAP: 0.7780 -> 0.8005Improved
add co-attention view (ablation)MVFNN · WikiQA testMAP: 0.7018 -> 0.7462Improved
add inquiry main verb view (ablation)MVFNN · WikiQA testMAP: 0.7319 -> 0.7462Improved
add inquiry type view (ablation)MVFNN · WikiQA testMAP: 0.7368 -> 0.7462Improved
add inquiry semantic view (ablation)MVFNN · WikiQA testMRR: 0.7576 -> 0.7576No clear effect
add residual link to simple BiLSTM fusion (ablation)BiLSTM view fusion · WikiQA testMAP: 0.7253 -> 0.7312Improved
use fusion RNN with gated external memory instead of BiLSTM+ResNet (ablation)MVFNN · WikiQA testMAP: 0.7312 -> 0.7462Improved
use fusion RNN with gated external memory instead of BiLSTM+ResNet (ablation)MVFNN · SemEval-2016 CQAMAP: 0.7911 -> 0.8005Improved
use MVFNN instead of Zhang et al. (2017) with extra featuresSemEval-2016 CQA · SemEval-2016 CQAMAP: 0.8014 vs 0.8005No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy