atlas

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

Replicate, Walk, and Stop on Syntax: An Effective Neural Network Model for Aspect-Level Sentiment Classification

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 47 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 syntax graph replicated random walk (vs mean-pool) (ablation)RepWalk · Rest14accuracy: 79.2 -> 83.8Helped
add syntax graph replicated random walk (vs mean-pool) (ablation)RepWalk · Twitteraccuracy: 72.1 -> 74.4Mixed
add dependency labels on edges (ablation)RepWalk · Rest14accuracy: 80.9 -> 83.8Helped
add pre-trained embeddings (ablation)RepWalk · Rest14accuracy: 81.8 -> 83.8Helped
add PoS tag embeddings (ablation)RepWalk · Rest14accuracy: 81.7 -> 83.8Helped
add Bi-GRU layer (ablation)RepWalk · Twitteraccuracy: 67.8 -> 74.4Helped
add Bi-GRU layer (ablation)RepWalk · Rest14accuracy: 79.3 -> 83.8Helped
use RepWalk instead of TNetaspect-level sentiment classifier · Twitteraccuracy: 75.0 -> 74.4Hurt

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