Research map / Vision-language and multimodal / Visual question answering
Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering
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 |
|---|---|---|---|
| jointly train answer selection with question-guided abstractive summarization | ASAS · WikiHowQA | MAP: 0.5022 -> 0.5522 | Helped |
| jointly train answer selection with question-guided abstractive summarization | ASAS · WikiHowQA | ROUGE 1: 27.32 -> 27.78 | Helped |
| add question-driven guidance to the pointer-generator | answer summarization · WikiHowQA | ROUGE 1: 26.83 -> 27.32 | Helped |
| add two-way attention between question and summary (ablation) | ASAS · WikiHowQA | MAP: 0.5208 -> 0.5522 | Helped |
| add the pointer network (ablation) | ASAS · WikiHowQA | MAP: 0.5341 -> 0.5522 | Helped |
| pre-train on WikiHowQA and fine-tune answer selection modules on the target domain (ablation) | ASAS · Travel | accuracy: 52.3 -> 56.5 | Helped |
| pre-train on WikiHowQA and fine-tune answer selection modules on the target domain (ablation) | ASAS · Cooking | accuracy: 45.8 -> 52.8 | Helped |
| pre-train on WikiHowQA and fine-tune answer selection modules on the target domain (ablation) | ASAS · Academia | accuracy: 39.9 -> 44.4 | Helped |
| pre-train on WikiHowQA and fine-tune answer selection modules on the target domain (ablation) | ASAS · Apple | accuracy: 30.9 -> 35.1 | Helped |
| pre-train on WikiHowQA and fine-tune answer selection modules on the target domain (ablation) | ASAS · Aviation | accuracy: 48.2 -> 52.9 | Helped |
Closest papers by meaning
- Community-Based Question Answering via Heterogeneous Social Network Learning (AAAI 2016 · similarity 0.91)
- COALA: A Neural Coverage-Based Approach for Long Answer Selection with Small Data (AAAI 2019 · similarity 0.90)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.85)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.85)
- Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers (NeurIPS 2025 · similarity 0.84)
- RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content (NeurIPS 2024 · similarity 0.84)
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.