AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Proposition Entailment in Educational Applications using Deep Neural Networks

Florin Bulgarov, Rodney Nielsen

AAAI 2018 · Label-efficient and robust learning › Knowledge distillation · approach: Teacher properties and robustness · 3 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
use 50-dim word embeddings with DNN instead of manual features with SVM (ablation)MMP entailment · MMP entailment testweighted F1: 0.73 -> 0.76Improved
use word embeddings instead of manual features in SVM (ablation)SVM · MMP entailment testF1 understood class: 0.53 -> 0.6Improved
add manual features to SVM with WEs (ablation)SVM (WEs) · MMP entailment testweighted F1: 0.75 -> 0.76No clear effect
add manual features to DNN with WEs (ablation)DNN (WEs) · MMP entailment testF1 understood class: 0.63 -> 0.55Hurt
add LSA score to SVM with manual features (ablation)SVM (man. ftrs.) · MMP entailment testweighted F1: 0.73 -> 0.73No clear effect
add LSA score to DNN with WEs (ablation)DNN (WEs) · MMP entailment testweighted F1: 0.76 -> 0.66Hurt
add Corley & Mihalcea score to DNN with WEs (ablation)DNN (WEs) · MMP entailment testweighted F1: 0.76 -> 0.65Hurt
add both LSA and C&M scores to DNN with WEs (ablation)DNN (WEs) · MMP entailment testweighted F1: 0.76 -> 0.66Hurt
increase word embedding dimension from 50 to 100 (ablation)DNN (WEs) · MMP entailment testweighted F1: 0.76 -> 0.73Hurt
increase word embedding dimension from 50 to 200 (ablation)DNN (WEs) · MMP entailment testweighted F1: 0.76 -> 0.74Hurt
use DNN with manual features instead of SVM (ablation)manual features · MMP entailment testweighted F1: 0.73 -> 0.72No clear effect
replace Horbach et al. state-of-the-art system with WE DNN (ablation)MMP entailment · MMP entailment testF1 understood class: 0.39 -> 0.63Improved

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