GSMNet: Global Semantic Memory Network for Aspect-Level Sentiment Classification

Aspect-level sentiment classification determines the sentiment polarity of a targeted aspect. To solve this task, attention-based neural networks are typically adopted to explore the interaction between the aspect and its context in a single sentence. However, such approaches ignore the rich semanti...

Full description

Saved in:
Bibliographic Details
Published in:IEEE intelligent systems 2021-09, Vol.36 (5), p.122-130
Main Authors: Liu, Zhiyue, Wang, Jiahai, Du, Xin, Rao, Yanghui, Quan, Xiaojun
Format: Article
Language:English
Subjects:
Active appearance model
attention mechanism
Classification
Data integration
Data mining
domain knowledge
Feature extraction
GSM
information fusion
Intelligent systems
Neural networks
Representations
semantic memory
Semantics
Sentences
Sentiment analysis
Sentiment classification
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aspect-level sentiment classification determines the sentiment polarity of a targeted aspect. To solve this task, attention-based neural networks are typically adopted to explore the interaction between the aspect and its context in a single sentence. However, such approaches ignore the rich semantic information that can be obtained from other sentences. This article shows that the contexts of aspects with similar meanings should be considered global semantic information that can be incorporated as domain knowledge. Then, a novel global semantic memory network (GSMNet) is proposed to share the global semantic information of various aspects and generate a domain-specific representation. With the help of domain knowledge, crucial words can be focused on more precisely. Moreover, instead of employing the concatenating operation for vectors before classification, GSMNet adopts a fine-grained information fusion layer to capture the importance of representations for efficiently extracting the valid parts of each dimension. The experimental results demonstrate the effectiveness of our model.
ISSN:1541-1672
1941-1294
DOI:10.1109/MIS.2020.3042253