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

Liang, Yunlong; Meng, Fandong; Zhang, Jinchao; Xu, Jinan; Chen, Yufeng; Zhou, Jie

doi:10.18653/v1/d19-1559

Cited by 46 publications

(27 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al (2018a) used targetspecific transformation networks to learn targetspecific word representations. Liang et al (2019) used aspect-guided recurrent transition networks to generate aspect-specific sentence representations. Sun et al (2019a) constructed aspect related auxiliary sentences as inputs to BERT (Devlin et al, 2019) for strong contextual encoders.…”

Section: Related Workmentioning

confidence: 99%

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Chen¹,

Teng

Zhang

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

100

View full text Add to dashboard Cite

Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task. However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory. To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs. We propose gating mechanisms to dynamically combine information from word dependency graphs and latent graphs which are learned by self-attention networks. Our model can complement supervised syntactic features with latent semantic dependencies. Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.

show abstract

Section: Related Workmentioning

confidence: 99%

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Chen¹,

Teng

Zhang

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

100

View full text Add to dashboard Cite

show abstract

“…MGAN (Fan et al, 2018) is an attention network based on BiLSTM that computes coarse-grained attention using averaged target embeddings and context words and leverages word ) is a CNN with two convolutional layers that use different nonlinear gating units to extract aspect-specific information. AGDT (Liang et al, 2019) contains an aspect-guided encoder which consists of an aspect-guided GRU and a deep transition GRU to extract aspect-specific sentence representation. Note that GCAE and AGDT can be extended for TBSA.…”

Section: Baselinesmentioning

confidence: 99%

“…Xue and Li (2018) extracts features from text using a convolutional layer and propagates the features to a max pooling layer based on either aspects or targets. Liang et al (2019) uses an aspect-guided encoder with an aspect-reconstruction step to generate either aspect-or target-specific sentence representation. The above models do not jointly consider aspects and targets and suffer when a target has conflicting sentiments toward different aspects.…”

Section: Aspect-based Sentiment Analysis (Absa)mentioning

confidence: 99%

“…These predefined domain aspects may or may not appear in the texts. Aspect-Based Sentiment Analysis (ABSA) approaches (Wang et al, 2016;Xue and Li, 2018;Liang et al, 2019) predict sentiments from text about a given aspect. And, Target-Based Sentiment Analysis (TBSA) approaches (Chen et al, 2017;Fan et al, 2018;Du et al, 2019; predict sentiments of targets that appear in an opinionated text.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis

Zhang

Hang

Singh

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding conflicting sentiments. Thus, a naive aggregation of sentiments from aspects and targets treated separately, as in existing sentiment analysis models, impairs performance.We propose Octa, 1 an approach that jointly considers aspects and targets when inferring sentiments. To capture and quantify relationships between targets and context words, Octa uses a selective self-attention mechanism that handles implicit or missing targets. Specifically, Octa involves two layers of attention mechanisms for, respectively, selective attention between targets and context words and attention over words based on aspects. On benchmark datasets, Octa outperforms leading models by a large margin, yielding (absolute) gains in accuracy of 1.6% to 4.3%.

show abstract

“…Xue and Li (2018) proposed to generate aspect categoryspecific representations based on convolutional neural networks and gating mechanisms. Since aspectrelated information may already be discarded and aspect-irrelevant information may be retained in an aspect independent encoder, some existing methods (Xing et al, 2019;Liang et al, 2019) utilized the given aspect to guide the sentence encoding from scratch. Recently, BERT based models Jiang et al, 2019) have obtained promising performance on the ACSA task.…”

Section: Introductionmentioning

confidence: 99%

Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis

Li¹,

Yin²,

Zhong³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Aspect-category sentiment analysis (ACSA) aims to predict sentiment polarities of sentences with respect to given aspect categories. To detect the sentiment toward a particular aspect category in a sentence, most previous methods first generate an aspect categoryspecific sentence representation for the aspect category, then predict the sentiment polarity based on the representation. These methods ignore the fact that the sentiment of an aspect category mentioned in a sentence is an aggregation of the sentiments of the words indicating the aspect category in the sentence, which leads to suboptimal performance. In this paper, we propose a Multi-Instance Multi-Label Learning Network for Aspect-Category sentiment analysis (AC-MIMLLN), which treats sentences as bags, words as instances, and the words indicating an aspect category as the key instances of the aspect category. Given a sentence and the aspect categories mentioned in the sentence, AC-MIMLLN first predicts the sentiments of the instances, then finds the key instances for the aspect categories, finally obtains the sentiments of the sentence toward the aspect categories by aggregating the key instance sentiments. Experimental results on three public datasets demonstrate the effectiveness of AC-MIMLLN 1 .

show abstract

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

Cited by 46 publications

References 51 publications

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis

Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis

Contact Info

Product

Resources

About