AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Entrainment2Vec: Embedding Entrainment for Multi-Party Dialogues

Zahra Rahimi, Diane Litman

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 13 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 weakly-supervised learned embedding instead of HAM baselineentrainment vectors · Conflict prediction (FS)accuracy: 69.74 -> 74.79Improved
use weakly-supervised learned embedding instead of HAM baselineentrainment vectors · Favorable prediction (all features)accuracy: 53.78 -> 63.86Improved
kernel initialization instead of uniform initialization (ablation)Self-supervised embedding (permuted negatives) · Conflict, FSaccuracy: 63.86 -> 73.95Improved
kernel initialization instead of uniform initialization (ablation)Self-supervised embedding (permuted negatives) · Favorable, all featuresaccuracy: 39.49 -> 57.14Improved
kernel initialization instead of uniform initialization (ablation)Self-supervised embedding (random negatives) · Favorable, all featuresaccuracy: 58.82 -> 56.30Hurt
permuted-conversation negative sampling instead of random negatives (ablation)Self-supervised kernel embedding · Conflict, FSaccuracy: 66.38 -> 73.95Improved
permuted negatives instead of random negatives (ablation)Self-supervised kernel embedding · Favorable, all featuresaccuracy: 56.30 -> 57.14Mixed
keep node embeddings fixed (not trainable) in weakly-supervised model (ablation)WeakS Kernel Permuted · Conflict, FSaccuracy: 63.86 -> 74.79Improved
keep node embeddings fixed (not trainable) (ablation)WeakS Kernel Permuted · Favorable, all featuresaccuracy: 56.30 -> 63.86Improved
train embedding (weakly-supervised) on top of kernel vectors (ablation)Kernel · Conflict, FSaccuracy: 69.74 -> 74.79Improved
kernel vectors without training vs HAMKernel · Conflict, all featuresaccuracy: 68.90 -> 57.14Hurt
add LASSO feature selection (ablation)Kernel embedding · Conflictaccuracy: 57.14 -> 69.74Improved

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