Aspect Level Sentiment Classification with Deep Memory Network

Abstract

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. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve the performance. Moreover, our approach is also fast. The deep memory network with 9 layers is 15 times faster than LSTM with a CPU implementation.

published in EMNLP 2016

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• Effective Approaches to Attention-based Neural Machine Translation
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• A Convolutional Neural Network for Modelling Sentences
• When Are Tree Structures Necessary for Deep Learning of Representations?
• Long Short-Term Memory Over Tree Structures
• Better Document-level Sentiment Analysis from RST Discourse Parsing

Cited by in corpus (22)

• Recent Trends in Deep Learning Based Natural Language Processing
• Understanding Neural Networks through Representation Erasure
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Deep Learning for Sentiment Analysis : A Survey
• Relational Graph Attention Network for Aspect-based Sentiment Analysis
• Description Based Text Classification with Reinforcement Learning
• Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
• Various Approaches to Aspect-based Sentiment Analysis
• Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
• Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
• Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
• Arabic aspect based sentiment analysis using bidirectional GRU based models
• DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
• Automatic coding of students' writing via Contrastive Representation Learning in the Wasserstein space
• CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding
• Which Review Aspect Has a Greater Impact on the Duration of Open Peer Review in Multiple Rounds? -- Evidence from Nature Communications
• Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
• Contextual and Position-Aware Factorization Machines for Sentiment Classification
• Dual Memory Network Model for Biased Product Review Classification
• Re-Evaluating GermEval17 Using German Pre-Trained Language Models
• Memory networks for consumer protection:unfairness exposed
• Imbalanced Sentiment Classification Enhanced with Discourse Marker