atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Gated Neural Networks for Targeted Sentiment Analysis

AAAI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 311 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
add bi-directional GRNN layer before pooling (ablation)pooling baseline · Targeted sentiment testaccuracy: 65.13 -> 69.65Helped
add three-way gated context interaction (G3) (ablation)pooling baseline · Targeted sentiment testaccuracy: 65.13 -> 67.79Helped
add G3 on top of GRNN (ablation)baseline+GRNN · Targeted sentiment testaccuracy: 69.65 -> 71.96Helped
add gates to recurrent layer (GRNN vs RNN) (ablation)baseline+RNN · Targeted sentiment devaccuracy: 68.05 -> 71.43Helped
add plain bi-directional RNN (ablation)pooling baseline · Targeted sentiment devaccuracy: 65.73 -> 68.05Helped
gated model vs Vo and Zhang (2015) with lexiconstargeted sentiment · Targeted sentiment testmacro F1: 65.56 -> 69.55Helped

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