AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Improving Event Causality Recognition with Multiple Background Knowledge Sources Using Multi-Column Convolutional Neural Networks

Canasai Kruengkrai, Kentaro Torisawa, Chikara Hashimoto, Julien Kloetzer, Jong-Hoon Oh, Masahiro Tanaka

AAAI 2017 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 70 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
replace single-column CNN with multi-column CNN (Base)CNN-SENT · Event causality test setaverage precision: 43.76 -> 49.34Improved
add all background knowledge sources (BP+WH+CL) (ablation)MCNN Base · Event causality test setaverage precision: 49.34 -> 55.13Improved
add short binary patterns (BP) (ablation)MCNN Base · Event causality test setaverage precision: 49.34 -> 54.32Improved
add why-QA answers (WH) (ablation)MCNN Base · Event causality test setaverage precision: 49.34 -> 52.03Improved
add clue-term sentences (CL) (ablation)MCNN Base · Event causality test setaverage precision: 49.34 -> 52.27Improved
add why-QA answer patterns (WH) as SVM featuresHashimoto14 SVM · Event causality test setaverage precision: 47.32 -> 43.41Hurt
add clue-term sentence patterns (CL) as SVM featuresHashimoto14 SVM · Event causality test setaverage precision: 47.32 -> 40.11Hurt
add short binary patterns (BP) as SVM featuresHashimoto14 SVM · Event causality test setaverage precision: 47.32 -> 47.39No clear effect
remove BP-overlapping short patterns from WH and CL inputs (ablation)Base+BP+WH+CL · Event causality test setaverage precision: 55.13 -> 55.42Improved
limit patterns to 15 for SVM baseline (ablation)Hashimoto14+BP+WH · Event causality test setaverage precision: 47.52 -> 47.88No clear effect
use Wikipedia-trained instead of in-domain word embeddings (ablation)Base+BP+WH+CL · Event causality test setaverage precision: 55.13 -> 54.84No clear effect
use random instead of pre-trained word embeddings (ablation)Base+BP+WH+CL · Event causality test setaverage precision: 55.13 -> 48.48Hurt

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