Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network

22 Feb 2020 Xuefeng Bai Pengbo Liu Yue Zhang

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their contexts... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Aspect-Based Sentiment Analysis MAMS RGAT+ Acc 84.52 # 1
Macro-F1 83.74 # 1
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Sub Task 2 RGAT+ Restaurant (Acc) 86.59 # 3
Laptop (Acc) 81.25 # 3
Mean Acc (Restaurant + Laptop) 83.92 # 3

Methods used in the Paper