Aspect Level Sentiment Classification with Deep Memory Network

We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect... (read more)

PDF Abstract EMNLP 2016 PDF EMNLP 2016 Abstract

Datasets


  Add Datasets introduced or used in this paper
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Aspect-Based Sentiment Analysis SemEval 2014 Task 4 Sub Task 2 MemNet Restaurant (Acc) 80.95 # 24
Laptop (Acc) 72.21 # 27
Mean Acc (Restaurant + Laptop) 76.58 # 26

Methods used in the Paper


METHOD TYPE
Sigmoid Activation
Activation Functions
Tanh Activation
Activation Functions
SVM
Non-Parametric Classification
Memory Network
Working Memory Models
LSTM
Recurrent Neural Networks