Research map / Vision-language and multimodal / Visual question answering
Assertion-Based QA With Question-Aware Open Information Extraction
Zhao Yan, Duyu Tang, Nan Duan, Shujie Liu, Wendi Wang, Daxin Jiang, Ming Zhou, Zhoujun Li
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 |
|---|---|---|---|
| Replace the flat Seq2Seq decoder with a hierarchical tuple- and word-level decoder | Seq2Seq · WebAssertions test | BLEU-4: 22.01 -> 35.76 | Improved |
| Add attention to Seq2Seq | Seq2Seq · WebAssertions test | BLEU-4: 22.01 -> 31.85 | Improved |
| Combine word-, phrase-, and sentence-level matching features (ablation) | ExtAst · WebAssertions test | MAP: 76.49% -> 77.99% | Improved |
| Add sentence-level semantic matching features (ablation) | ExtAst · WebAssertions test | P@1: 47.62% -> 63.34% | Improved |
| Add question-aware ExtAst assertion features | Baseline answer selection · WikiQA | MAP: 69.89% -> 72.33% | Improved |
| Add question-aware ExtAst assertion features | Baseline answer selection · MARCO | MAP: 45.97% -> 50.07% | Improved |
| Add Seq2Ast assertion features | Baseline answer selection · MARCO | MAP: 45.97% -> 47.44% | Improved |
| Add a randomly selected Open IE assertion feature | Baseline answer selection · WikiQA | MAP: 69.89% -> 69.17% | Hurt |
| Add max-pooled Open IE assertion features | Baseline answer selection · MARCO | MAP: 45.97% -> 49.37% | Improved |
Closest papers by meaning
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.87)
- A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering (NeurIPS 2026 · similarity 0.86)
- ChatQA: Surpassing GPT-4 on Conversational QA and RAG (NeurIPS 2024 · similarity 0.86)
- RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content (NeurIPS 2024 · similarity 0.86)
- Code-Style In-Context Learning for Knowledge-Based Question Answering (AAAI 2024 · similarity 0.86)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · 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.
