Research map / Vision-language and multimodal / Visual question answering
An Unsupervised Model With Attention Autoencoders for Question Retrieval
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 |
|---|---|---|---|
| Add lexical mismatch information (ablation) | RAMN base model · SemEval-2016 Task 3 Subtask B | MAP: 73.05 -> 75.92; 2.87 MAP points | Helped |
| Add lexical mismatch information (ablation) | RAMN base model · SemEval-2017 Task 3 Subtask B | MAP: 45.36 -> 47.40; 2.04 points | Helped |
| Add initial search rank (ablation) | RAMN with lexical mismatch · SemEval-2016 Task 3 Subtask B | MAP: 75.92 -> 77.79; 1.87 | Helped |
| Add initial search rank (ablation) | RAMN with lexical mismatch · SemEval-2017 Task 3 Subtask B | MAP: 47.40 -> 48.53; 1.13 | Helped |
| Use attention autoencoders instead of RNN autoencoders (ablation) | RAMN semantic matching base model · SemEval-2016 Task 3 Subtask B | MAP: 71.76 -> 73.05; 1.29 MAP points | Helped |
| Use attention autoencoders instead of RNN autoencoders (ablation) | RAMN semantic matching base model · SemEval-2017 Task 3 Subtask B | MAP: 43.59 -> 45.36; 1.77 MAP points | Helped |
| Use attention autoencoders instead of RNN autoencoders (ablation) | Full RAMN · SemEval-2016 Task 3 Subtask B | MAP: 77.06 -> 77.79 | Helped |
| Use attention autoencoders instead of RNN autoencoders (ablation) | Full RAMN · SemEval-2017 Task 3 Subtask B | MAP: 46.38 -> 48.53 | Helped |
Closest papers by meaning
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.88)
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (AAAI 2017 · similarity 0.87)
- Semantic Sentence Matching with Densely-Connected Recurrent and Co-Attentive Information (AAAI 2019 · similarity 0.86)
- A Question-Focused Multi-Factor Attention Network for Question Answering (AAAI 2018 · similarity 0.86)
- Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge (NeurIPS 2026 · similarity 0.86)
- UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models (AAAI 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.