Research map / Vision-language and multimodal / Visual question answering
Word Embedding Based Correlation Model for Question/Answer Matching
Yikang Shen, Wenge Rong, Nan Jiang, Baolin Peng, Jie Tang, Zhang Xiong
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 |
|---|---|---|---|
| add CNN to WEC (ablation) | WEC question-answer matching · Yahoo! Answers Travel, Relationships, and Finance | DCG@1: 0.734 -> 0.761; 0.698 -> 0.709; 0.761 -> 0.780 | Improved |
| add CNN to WEC (ablation) | WEC question-answer matching · Yahoo! Answers Relationships and Finance | DCG@6: 0.936 -> 0.938; 0.949 -> 0.952 | Improved |
| add CNN to WEC (ablation) | WEC question-answer matching · Yahoo! Answers Travel | DCG@6: 0.946 -> 0.946 | No clear effect |
| add CNN to WEC (ablation) | WEC question-answer matching · Baidu Zhidao Computers & Internet, Education & Science, Games, and Entertainment & Recreation | DCG@1: 0.821 -> 0.826; 0.838 -> 0.870; 0.692 -> 0.703; 0.778 -> 0.780 | Improved |
| add CNN to WEC (ablation) | WEC question-answer matching · Baidu Zhidao Computers & Internet, Education & Science, Games, and Entertainment & Recreation | DCG@6: 0.968 -> 0.970; 0.975 -> 0.980; 0.937 -> 0.941; 0.962 -> 0.963 | Improved |
| use WEC instead of TRLM (IBM-1) | Question-answer matching · Baidu Zhidao Education & Science | DCG@1: 0.843 -> 0.838 | Hurt |
| use co-occurrence-based IBM-1 translation probabilities instead of cosine-similarity translation probabilities | TM and TRLM · Baidu Zhidao categories | DCG@1 | Improved |
| use lexical-overlap retrieval models rather than WEC | Question-answer matching · Yahoo! Answers and Baidu Zhidao | DCG | Hurt |
Closest papers by meaning
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (AAAI 2017 · similarity 0.87)
- Hybrid Attentive Answer Selection in CQA With Deep Users Modelling (AAAI 2018 · similarity 0.86)
- A General Framework for Producing Interpretable Semantic Text Embeddings (ICLR 2025 · similarity 0.84)
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (AAAI 2024 · similarity 0.84)
- Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers (NeurIPS 2025 · similarity 0.84)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.83)
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.
