Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis

@inproceedings{Tang2019ProgressiveSA,
  title={Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis},
  author={Jialong Tang and Ziyao Lu and Jinsong Su and Yubin Ge and Linfeng Song and Le Sun and Jiebo Luo},
  booktitle={ACL},
  year={2019}
}
In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. [] Key Method Specifically, we iteratively conduct sentiment predictions on all training instances.

Figures and Tables from this paper

Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning

DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis

A Deep Neural Network (DNN) driven GML approach for ATSA is proposed, which uses an unsupervised neural network to cluster the automatically extracted features by their sentiment orientation and models the clustered features as factors to enable implicit knowledge conveyance for gradual inference in a factor graph.

Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis

A graph attention network with memory fusion is proposed to extend GCN’s idea by assigning different weights to edges by assigning equal weight to all the edges between connected words.

Multiple Interactive Attention Networks for Aspect-Based Sentiment Classification

A Multiple Interactive Attention Network (MIN) is proposed that takes the target word and the context word as the core to obtain and fuse the interactive information and experimental results showed that the model was much more effective.

A multi-task learning network using shared BERT models for aspect-based sentiment analysis

This work uses a shared BERT model to construct a multi-task learning network, which is trained by strongly and weakly related tasks, and uses amulti-head self-attention layer to replace a linear layer in traditional multi- task learning networks, to enhance the ability to capture global semantics.

Aspect-Level Sentiment Analysis via a Syntax-Based Neural Network

This work proposes a reliable syntax-based neural network model that performs a thorough search on the syntax graph to effectively find the relevant contextual information with respect to the aspect term for the sentence encoding in aspect-level sentiment classification.

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

A neural network model named RepWalk is presented which performs a replicated random walk on a syntax graph, to effectively focus on the informative contextual words and suggests that the method for incorporating syntactic structure enriches the representation for the ALSC classification.

Aspect-Based Sentiment Analysis for User Reviews

A deep-level semiself-help sentiment annotation system based on the bidirectional encoder representation from transformers (BERT) weakly supervised classifier to address the problems of insufficient data and low label accuracy and can significantly reduce the quantity of data annotation engineering required.

A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis

A novel Aspect-Guided Deep Transition model, named AGDT, is proposed, which utilizes the given aspect to guide the sentence encoding from scratch with the specially-designed deep transition architecture, and an aspect-oriented objective is designed to enforce AGDT to reconstruct thegiven aspect with the generated sentence representation.

References

SHOWING 1-10 OF 27 REFERENCES

Attention-based LSTM for Aspect-level Sentiment Classification

This paper reveals that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect, and proposes an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.

Interactive Attention Networks for Aspect-Level Sentiment Classification

It is argued that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning and proposed the interactive attention networks (IAN) to interactively learn attentions in the contexts and targets.

Transformation Networks for Target-Oriented Sentiment Classification

A new model is proposed to overcome the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this sentiment classification task, and employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer.

Aspect Level Sentiment Classification with Deep Memory Network

A deep memory network for aspect level sentiment classification that explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect, and is also fast.

Effective LSTMs for Target-Dependent Sentiment Classification

Two target dependent long short-term memory models, where target information is automatically taken into account, are developed, which achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.

SemEval-2014 Task 4: Aspect Based Sentiment Analysis

SemEval2014 Task 4 aimed to foster research in the field of aspect-based sentiment analysis, where the goal is to identify the aspects of given target entities and the sentiment expressed for each aspect.

Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs

This work presents a novel deep learning method that relies on hierarchical LSTMs to model the multiple sentences that contain the person names of interests, and introduces supervised attention mechanisms based on semantical word lists and dependency trees to upweight the important contextual words.

NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews

Submissions to SemEval-2014 stood first in detecting aspect categories, first in detects sentiment towards aspects categories, third in detecting aspects terms, and first and second in detecting sentiment towards aspect terms in the laptop and restaurant domains, respectively.

Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification

AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them and it is shown that AdaRNN improves the baseline methods.

Neural Machine Translation with Deep Attention

A deep attention model (DeepAtt) is proposed that is capable of automatically determining what should be passed or suppressed from the corresponding encoder layer so as to make the distributed representation appropriate for high-level attention and translation.