Research map / Vision-language and multimodal / Visual question answering
Hybrid Attentive Answer Selection in CQA With Deep Users Modelling
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 hybrid attention (intra-sentence plus entropy-based inter-sentence) with user modelling instead of best baseline AI-CNN | UIA-LSTM-CNN · SemEval-2016 Task 3 | MAP: 0.7891 -> 0.8086 | Helped |
| Model users from their written answers and attend to question parts, versus learning user embeddings from user-question relations (AMRNL) | UIA-LSTM-CNN · SemEval-2016 Task 3 | MAP: 0.7043 -> 0.8086 | Helped |
| Hidden size beyond 128 or below it (ablation) | UIA-LSTM-CNN · SemEval-2016 Task 3 | MAP | Hurt |
| Vary number of stacked LSTM layers (ablation) | UIA-LSTM-CNN · SemEval-2016 Task 3 | MAP | No clear effect |
Closest papers by meaning
- Attentive Interactive Neural Networks for Answer Selection in Community Question Answering (AAAI 2017 · similarity 0.92)
- COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data (AAAI 2019 · similarity 0.90)
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (AAAI 2017 · similarity 0.89)
- Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering (AAAI 2020 · similarity 0.89)
- Community-Based Question Answering via Heterogeneous Social Network Learning (AAAI 2016 · similarity 0.89)
- Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions (ICLR 2025 · 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.