atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain text and graph transfer · 167 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
HATNh vs best baseline AMNcross-domain sentiment · Amazon reviewsaccuracy: 0.8279 -> 0.8661Helped
add NP-net (non-pivot network) to P-net (ablation)P-net · Amazon reviewsaccuracy: 0.8556 -> 0.8620Helped
add P-net to NP-net (ablation)NP-net · Amazon reviewsaccuracy: 0.7949 -> 0.8620Helped
add hierarchical positional encoding (ablation)HATN · Amazon reviewsaccuracy: 0.8620 -> 0.8661Helped
add word-level attention to sentence-only attention (hierarchical) (ablation)P-net · Amazon reviewsaccuracy: 83.66% -> 0.8556Helped
use hierarchical attention instead of word-only attention (AMN)P-net · Amazon reviewsaccuracy: 0.8279 -> 0.8556Helped
add hierarchical positional encoding (ablation)HATN · Amazon reviews E->Vaccuracy: 0.8455 -> 0.8418Hurt

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