Research map / Vision-language and multimodal / Visual question answering
Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering
Yang Deng, Yuexiang Xie, Yaliang Li, Min Yang, Nan Du, Wei Fan, Kai Lei, Ying Shen
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 |
|---|---|---|---|
| Jointly train answer selection and KBQA instead of training tasks separately | MTQA-net · Yahoo QA | P@1: 0.737 -> 0.752 | Improved |
| Jointly train answer selection and KBQA instead of training tasks separately | MTQA-net · SimpleQuestions | Accuracy: 0.913 -> 0.922 | Improved |
| Add multi-view attention to joint training | MVA-MTQA-net · Yahoo QA | P@1: 0.806 -> 0.833 | Improved |
| Add multi-view attention to joint training | MVA-MTQA-net · SimpleQuestions | Accuracy: 0.931 -> 0.957 | Improved |
| Add word view attention (ablation) | MVA-MTQA-net (MTL) · Yahoo QA | P@1: 0.824 -> 0.833 | Improved |
| Add knowledge view attention (ablation) | MVA-MTQA-net (MTL) · SimpleQuestions | Accuracy: 0.944 -> 0.957 | Improved |
| Add semantic view attention (ablation) | MVA-MTQA-net (MTL) · Yahoo QA | MRR: 0.886 -> 0.909 | Improved |
| Add knowledge semantic view attention (ablation) | MVA-MTQA-net (MTL) · TREC QA | MAP: 0.793 -> 0.811 | Improved |
| Add co-attention view (ablation) | MVA-MTQA-net (MTL) · WebQSP | Accuracy: 0.829 -> 0.858 | Improved |
| Add co-attention view (ablation) | MVA-MTQA-net (MTL) · Yahoo QA | P@1: 0.811 -> 0.833 | Improved |
Closest papers by meaning
- Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms (AAAI 2025 · similarity 0.88)
- Code-Style In-Context Learning for Knowledge-Based Question Answering (AAAI 2024 · similarity 0.87)
- Cost-efficient Knowledge-based Question Answering with Large Language Models (NeurIPS 2024 · similarity 0.86)
- KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search (ICML 2025 · similarity 0.86)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.86)
- Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions (ICLR 2025 · 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.
