AI Paper Atlas

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

AAAI 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 49 citations (OpenAlex)

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 changedWhereMeasuredEffect
add CNN to WEC (ablation)WEC question-answer matching · Yahoo! Answers Travel, Relationships, and FinanceDCG@1: 0.734 -> 0.761; 0.698 -> 0.709; 0.761 -> 0.780Improved
add CNN to WEC (ablation)WEC question-answer matching · Yahoo! Answers Relationships and FinanceDCG@6: 0.936 -> 0.938; 0.949 -> 0.952Improved
add CNN to WEC (ablation)WEC question-answer matching · Yahoo! Answers TravelDCG@6: 0.946 -> 0.946No clear effect
add CNN to WEC (ablation)WEC question-answer matching · Baidu Zhidao Computers & Internet, Education & Science, Games, and Entertainment & RecreationDCG@1: 0.821 -> 0.826; 0.838 -> 0.870; 0.692 -> 0.703; 0.778 -> 0.780Improved
add CNN to WEC (ablation)WEC question-answer matching · Baidu Zhidao Computers & Internet, Education & Science, Games, and Entertainment & RecreationDCG@6: 0.968 -> 0.970; 0.975 -> 0.980; 0.937 -> 0.941; 0.962 -> 0.963Improved
use WEC instead of TRLM (IBM-1)Question-answer matching · Baidu Zhidao Education & ScienceDCG@1: 0.843 -> 0.838Hurt
use co-occurrence-based IBM-1 translation probabilities instead of cosine-similarity translation probabilitiesTM and TRLM · Baidu Zhidao categoriesDCG@1Improved
use lexical-overlap retrieval models rather than WECQuestion-answer matching · Yahoo! Answers and Baidu ZhidaoDCGHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy