Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks

Zhang, Chen; Li, Qiuchi; Song, Dawei

doi:10.48550/arxiv.1909.03477

Cited by 20 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…dependency tree) based on dependency relations using a RNN and compute the node distances as attention weight. Recently, graph convolutional networks (GCNs) (Zhang, Li, and Song 2019) have been used to explore the dependencies between contexts by incorporating dependency trees into attention models to improve performance. In another work, (Tang et al 2020) propose DGEDT based on aspect and dependency graphs and improve the shortcomings of the instability and noisy information of the dependency tree.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification

Cao¹,

Tang²,

Wei³

et al. 2021

Preprint

View full text Add to dashboard Cite

Aspect-based sentiment classification aims to predict the sentiment polarity of a specific aspect in a sentence. However, most existing methods attempt to construct dependency relations into a homogeneous dependency graph with the sparsity and ambiguity, which cannot cover the comprehensive contextualized features of short texts or consider any additional node types or semantic relation information. To solve those issues, we present a sentiment analysis model named Isomer, which performs a dual-channel attention on heterogeneous dependency graphs incorporating external knowledge, to effectively integrate other additional information. Specifically, a transfer-enhanced dual-channel heterogeneous dependency attention network is devised in Isomer to model short texts using heterogeneous dependency graphs. These heterogeneous dependency graphs not only consider different types of information but also incorporate external knowledge. Experiments studies show that our model outperforms recent models on benchmark datasets. Furthermore, the results suggest that our method captures the importance of various information features to focus on informative contextual words.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Recently, graph convolutional networks (GCNs) (Zhang, Li, and Song 2019) have been used to explore the dependency relations between contexts incorporating the dependency tree structure of a sentence. Most studies mentioned above apply homogeneous dependency graphs and dependency trees to represent contextual syntactic and dependencies.…”

Section: Introductionmentioning

confidence: 99%

Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification

Cao¹,

Tang²,

Wei³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…By internally infusing the semantics of the neighboring nodes, the popular Graph Convolutional Network (GCN) (Kipf and Welling, 2016) and Graph Attention Network (GAT) (Veličković et al, 2017) have shown great success in semisupervised node classification when the number of labeled nodes is limited. Graph neural networks have been applied for many NLP tasks such as text classification Zhang et al, 2019a;, semantic role labeling (Marcheggiani and Titov, 2017), machine translation (Beck et al, 2018), question answering (Song et al, 2018;Saxena et al, 2020), information extraction Vashishth et al, 2018;Nguyen and Grishman, 2018;Sahu et al, 2019;Fu et al, 2019;Zhang et al, 2019b), etc. In our work, we proposed to use graph neural networks to learn new labeling rules.…”

Section: Related Workmentioning

confidence: 99%

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

Zhao¹,

Ding²,

Feng³

2021

Preprint

View full text Add to dashboard Cite

Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often requires a considerable amount of manual effort and domain expertise. To alleviate this problem, we propose GLARA, a graph-based labeling rule augmentation framework, to learn new labeling rules from unlabeled data. We first create a graph with nodes representing candidate rules extracted from unlabeled data. Then, we design a new graph neural network to augment labeling rules by exploring the semantic relations between rules. We finally apply the augmented rules on unlabeled data to generate weak labels and train a NER model using the weakly labeled data. We evaluate our method on three NER datasets and find that we can achieve an average improvement of +20% F1 score over the best baseline when given a small set of seed rules.

show abstract

“…The datasets that correspond to these domains came from different sources. While most of work conducted so far in restaurants and technology reviews came from the readily SemEval series of evaluations of computational semantic analysis systems, with readily labelled datasets, authors of other papers also used datasets from Sentihood [4,7]; Twitter [9,13,19,20,27,28]; Amazon [18]; Yelp [18]; Coursera [22], online market [21], to name a few. Manual data collection was performed in [11] using Web Crawler and APIs to collect restaurant and hotel reviews (2000 and 4000 respectively).…”

Section: Datasets and Application Domainsmentioning

confidence: 99%

Aspect-Based Sentiment Analysis in Education Domain

Hajrizi,

Nuçi

2020

Preprint

View full text Add to dashboard Cite

Analysis of a large amount of data has always brought value to institutions and organizations. Lately, people's opinions expressed through text have become a very important aspect of this analysis. In response to this challenge, a natural language processing technique known as Aspect-Based Sentiment Analysis (ABSA) has emerged. Having the ability to extract the polarity for each aspect of opinions separately, ABSA has found itself useful in a wide range of domains. Education is one of the domains in which ABSA can be successfully utilized. Being able to understand and find out what students like and don't like most about a course, professor, or teaching methodology can be of great importance for the respective institutions. While this task represents a unique NLP challenge, many studies have proposed different approaches to tackle the problem. In this work, we present a comprehensive review of the existing work in ABSA with a focus in the education domain. A wide range of methodologies are discussed and conclusions are drawn. KeywordsAspect-based sentiment analysis • aspect category extraction • polarity evaluation • text mining • education • course reviews • supervised learning • unsupervised learning • data pre-processing • machine learning models

show abstract

Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks

Cited by 20 publications

References 24 publications

Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification

Isomer: Transfer enhanced Dual-Channel Heterogeneous Dependency Attention Network for Aspect-based Sentiment Classification

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

Aspect-Based Sentiment Analysis in Education Domain

Contact Info

Product

Resources

About