Document-Level Multi-Aspect Sentiment Classification as Machine Comprehension

Yin, Yichun; Song, Yangqiu; Ming, Zhang

doi:10.18653/v1/d17-1217

Cited by 71 publications

(48 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We conduct our experiments on three public datasets on DASC, i.e., TripUser , TripAdvisor (Wang et al, 2010) and BeerAdvocate (McAuley et al, 2012;Lei et al, 2016). In the experiment, we adopt Discourse Segmentation and those with ‡ are from Yin et al (2017) Tool 3 to segment all reviews in the three datasets into EDUs (i.e., clauses). Moreover, we adopt training/development/testing settings (8:1:1) by following Yin et al (2017); .…”

Section: Experimental Settingsmentioning

confidence: 99%

“…In the experiment, we adopt Discourse Segmentation and those with ‡ are from Yin et al (2017) Tool 3 to segment all reviews in the three datasets into EDUs (i.e., clauses). Moreover, we adopt training/development/testing settings (8:1:1) by following Yin et al (2017); . Table 1 shows the statistics of the three datasets.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…The performance is evaluated using Accuracy (Acc.) and MSE as Yin et al (2017). Moreover, t-test is used to evaluate the significance of the performance difference between two approaches (Yang and Liu, 1999).…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Baselines. We compare HRL with the following baselines: 1) SVM (Yin et al, 2017). This approach only adopts unigram, bigram as features to train an SVM classifier.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…The goal of DASC is to predict the rating score towards each aspect by analyzing the whole document. In the last decade, this task has been drawing more and more interests of researchers in the Natural Language Processing community (Titov and McDonald, 2008;Yin et al, 2017;. In previous studies, neu- ral models have shown to be effective for performance improvement on DASC.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Wang¹,

Sun²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper, to simulating the steps of analyzing aspect sentiment in a document by human beings, we propose a new Hierarchical Reinforcement Learning (HRL) approach to DASC. This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC. First, a high-level policy is proposed to select aspect-relevant clauses and discard noisy clauses. Then, a low-level policy is proposed to select sentiment-relevant words and discard noisy words inside the selected clauses. Finally, a sentiment rating predictor is designed to provide reward signals to guide both clause and word selection. Experimental results demonstrate the impressive effectiveness of the proposed approach to DASC over the state-of-the-art baselines. * Corresponding author Review Document [ [ [This hotel is close to railway station] ] ]Clause1 [ [ [and very convenient to eat around] ] ]Clause2 [ [ [but room of Hilton is a little uncomfortable .]Clause3 [ [ [I'm often nitpicking for room decoration.] ] ]Clause4 [ [ [Besides, the price is very expensive ] ] ]Clause5 [ [ [although the staff service is professional .] ] ]Clause6

show abstract

Section: Experimental Settingsmentioning

confidence: 99%

Section: Experimental Settingsmentioning

confidence: 99%

Section: Experimental Settingsmentioning

confidence: 99%

“…Baselines. We compare HRL with the following baselines: 1) SVM (Yin et al, 2017). This approach only adopts unigram, bigram as features to train an SVM classifier.…”

Section: Experimental Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Wang¹,

Sun²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

Deep learning for sentiment analysis: A survey

Zhang

Wang

Liu

2018

WIREs Data Min & Knowl

1,176

622

View full text Add to dashboard Cite

Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state‐of‐the‐art prediction results. Along with the success of deep learning in many application domains, deep learning is also used in sentiment analysis in recent years. This paper gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis. This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Algorithmic Development > Text Mining

show abstract

Semantic Similarity Measures to Disambiguate Terms in Medical Text

Lei

Huang

et al. 2018

Neural Information Processing

View full text Add to dashboard Cite

Document-Level Multi-Aspect Sentiment Classification as Machine Comprehension

Cited by 71 publications

References 26 publications

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Deep learning for sentiment analysis: A survey

Semantic Similarity Measures to Disambiguate Terms in Medical Text

Contact Info

Product

Resources

About