Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

Over the last decade, aspect-based sentiment analysis (ABSA) has been a rapidly growing field of natural language processing [1]. ABSA is a fine-grained sentiment analysis task which aims at detecting the polarity of an entity or an entity's attribute [2]. In ABSA, the aspect can be divided into two levels: aspect term (also called aspect target) and aspect category. An example sentence is provided in Fig. 1. For the sentence "Best Pastrami I ever had and great portion without being ridiculous, " the aspect terms are "Pastrami" and "portions, " respectively. Aspect categories are "FOOD#QUALITY" and "FOOD#STYLE_OPTIONS. " Obviously, a satisfactory method for an ABSA task should be applicable at both aspect levels. In the early days, traditional machine learning methods dominated as the method for an ABSA task, such as Support Vector Machine (SVM) [3]. However, these methods need feature engineering which is time consuming and laborious. Recently, deep learning methods have become increasingly popular for the sentiment analysis task, such as

show abstract

“…10. Word&Clause-Level ATT [39]: This approach employs word-level and clause-level attentions to predict sentiment. 11.…”

Section: Table 1 the Statistical Information Of All Datasetsmentioning

confidence: 99%

Attention-based Sentiment Reasoner for aspect-based sentiment analysis

Liu

Shen

Zhang

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…And attention layer assigned weight to each word in sentences. In addition, Wang et al [26] proposed a hierarchical network on both word-level and clause-level attentions for ASC, which focuses on the relationship of all clauses using the attention mechanism.…”

Section: B Attention Network For Ascmentioning

confidence: 99%

Interactive Multi-Head Attention Networks for Aspect-Level Sentiment Classification

Zhang

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Aspect-level sentiment classification (ASC) has received much attention these years. With the successful application of attention networks in many fields, attention-based ASC has aroused great interest. However, most of the previous methods did not analyze the contribution of words well and the contextaspect term interaction was not well implemented, which largely limit the efficacy of models. In this paper, we exploit a novel method that is efficient and mainly adopts Multi-head Attention (MHA) networks. First, the word embedding and aspect term embedding are pre-trained by Bidirectional Encoder Representations from Transformers (BERT). Second, we make full use of MHA and convolutional operation to obtain hidden states, which is superior to traditional neural networks. Then, the interaction between context and aspect term is further implemented through averaging pooling and MHA. We conduct extensive experiments on three benchmark datasets and the final results show that the Interactive Multi-head Attention Networks (IMAN) model consistently outperforms the state-of-the-art methods on ASC task. INDEX TERMS Natural language processing, aspect-level, sentiment classification, attention mechanism.

show abstract

“…In recent years, attention mechanism [9] has been successfully extensive applications in many natural language processing (NLP) tasks [10], such as text generation [11], [12], machine translation [13], [14] and question answering [15], [16]. Sentiment analysis models for aspect-level have recently been introduced attention mechanism to models and achieved great results [17]- [20]. Both industry and academia have realized the importance of the aspect-level sentiment analysis, and made attempts to model the relationship by designing a series of attention models [21].…”

Section: Introductionmentioning

confidence: 99%

Interactive Rule Attention Network for Aspect-Level Sentiment Analysis

Zhu

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Aspect-level sentiment analysis is a fundamental task in NLP, and it aims to predict the sentiment polarity of each specific aspect term in a given sentence. Recent researches show that the finegrained sentiment analysis for aspect-level has become a research hotspot. However, previous work did not consider the influence of grammatical rules on aspect-level sentiment analysis. In addition, attention mechanism is too simple to learn attention information from context and target interactively. Therefore, we propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis. IRAN not only designs a grammar rule encoder, which simulates the grammatical functions at the sentence by standardizing the output of adjacent positions, but also constructs an interaction attention network to learn attention information from context and target. Experimental results on SemEval 2014 Dataset and ACL 2014 Twitter Dataset demonstrate IRAN can learn effective features and obtain superior performance over the baseline models. INDEX TERMS Aspect-level sentiment analysis, grammatical rules, IRAN, interaction attention network.

show abstract

Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks

Cited by 83 publications

References 1 publication

Attention-based Sentiment Reasoner for aspect-based sentiment analysis

Attention-based Sentiment Reasoner for aspect-based sentiment analysis

Interactive Multi-Head Attention Networks for Aspect-Level Sentiment Classification

Interactive Rule Attention Network for Aspect-Level Sentiment Analysis

Contact Info

Product

Resources

About