Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification

Du, Chunning; Sun, Haifeng; Wang, Jingyu; Qi, Qi; Liao, Jianxin; Tian, Xu; Liu, Ming

doi:10.18653/v1/d19-1551

Cited by 60 publications

(24 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following works include applying memory network-based ( Tang, Qin & Liu, 2016 ) and attention-based ( Chen et al, 2017 ) method to LSTM models, involving two stacked LSTMs ( Xu et al, 2020 ) and so on. More recent models such as capsule network ( Chen & Qian, 2019 ; Du et al, 2019 ), graph convolutional network model ( Zhang, Li & Song, 2019 ), graph attention network ( Wang et al, 2020 ), bi-level interactive graph convolution network ( Zhang & Qian, 2020 ) are also used for ABSA task. Zhu et al, (2019) have exploited the interaction between the aspect category and the contents under the guidance of both sentiment polarity and predefined categories, and the proposed aspect aware learning framework has achieved satisfying performance in ABSA.…”

Section: Literature Reviewsmentioning

confidence: 99%

One for “All”: a unified model for fine-grained sentiment analysis under three tasks

Yang²,

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Background Fine-grained sentiment analysis is used to interpret consumers’ sentiments, from their written comments, towards specific entities on specific aspects. Previous researchers have introduced three main tasks in this field (ABSA, TABSA, MEABSA), covering all kinds of social media data (e.g., review specific, questions and answers, and community-based). In this paper, we identify and address two common challenges encountered in these three tasks, including the low-resource problem and the sentiment polarity bias. Methods We propose a unified model called PEA by integrating data augmentation methodology with the pre-trained language model, which is suitable for all the ABSA, TABSA and MEABSA tasks. Two data augmentation methods, which are entity replacement and dual noise injection, are introduced to solve both challenges at the same time. An ensemble method is also introduced to incorporate the results of the basic RNN-based and BERT-based models. Results PEA shows significant improvements on all three fine-grained sentiment analysis tasks when compared with state-of-the-art models. It also achieves comparable results with what the baseline models obtain while using only 20% of their training data, which demonstrates its extraordinary performance under extreme low-resource conditions.

show abstract

Section: Literature Reviewsmentioning

confidence: 99%

One for “All”: a unified model for fine-grained sentiment analysis under three tasks

Yang²,

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Our work is inspired by the work of capsule graph neural network [28], especially its application on aspect extraction [3,5]. These works mainly focus on capsule networks for aspect-level sentiment classification.…”

Section: Related Workmentioning

confidence: 99%

Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network

Zhao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Personalized review generation (PRG) aims to automatically produce review text reflecting user preference, which is a challenging natural language generation task. Most of previous studies do not explicitly model factual description of products, tending to generate uninformative content. Moreover, they mainly focus on word-level generation, but cannot accurately reflect more abstractive user preference in multiple aspects. To address the above issues, we propose a novel knowledgeenhanced PRG model based on capsule graph neural network (Caps-GNN). We first construct a heterogeneous knowledge graph (HKG) for utilizing rich item attributes. We adopt Caps-GNN to learn graph capsules for encoding underlying characteristics from the HKG. Our generation process contains two major steps, namely aspect sequence generation and sentence generation. First, based on graph capsules, we adaptively learn aspect capsules for inferring the aspect sequence. Then, conditioned on the inferred aspect label, we design a graph-based copy mechanism to generate sentences by incorporating related entities or words from HKG. To our knowledge, we are the first to utilize knowledge graph for the PRG task. The incorporated KG information is able to enhance user preference at both aspect and word levels. Extensive experiments on three real-world datasets have demonstrated the effectiveness of our model on the PRG task. CCS CONCEPTS • Computing methodologies → Natural language generation.

show abstract

“…To investigate the impact of different components of our proposed adversarial multi-task learning framework, we conduct experiments based on RAM model and report the results of different structures 6 . As shown in Table 2, Simply incorporation synthetic samples (w/ synthetic) only leads to marginal improvements since some of the synthetic samples may introduce noise to the training process.…”

Section: Ablation Studymentioning

confidence: 99%

Aspect-invariant Sentiment Features Learning: Adversarial Multi-task Learning for Aspect-based Sentiment Analysis

Liang

Yin

Gui

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

In most previous studies, information about aspects in sentences is considered important for the Aspect-based Sentiment Analysis (ABSA task and therefore various attention mechanisms have been explored to leverage interactions between aspects and context. However, some sentiment expressions carry the same polarity regardless of the aspects they are associated with. In such cases, it is not necessary to incorporate aspect information for ABSA. In fact, in our experiments, we find that blindly leveraging interactions between aspects and context as features may introduce noise when analyzing those aspect-invariant sentiment expressions, especially when facing with limited aspect-related annotated data. Hence, in this paper, we propose an Adversarial Multi-task Learning Framework to identify the aspect-invariant/dependent sentiment expressions automatically without requiring extra annotations. In addition, we use a gating mechanism to control the contribution of representations derived from aspect-invariant and aspect-dependent hidden states when generating the final contextual sentiment representations for the given aspect. This essentially allows the exploitation of aspectinvariant sentiment features for better ABSA results. Experimental results on two benchmark datasets show that extending existing neural models using our proposed framework achieves superior performance. In addition, the aspect-invariant data extracted by our framework can be considered as pivot features for better transfer learning of the ABSA models on unseen aspects.

show abstract

Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification

Cited by 60 publications

References 21 publications

One for “All”: a unified model for fine-grained sentiment analysis under three tasks

One for “All”: a unified model for fine-grained sentiment analysis under three tasks

Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network

Aspect-invariant Sentiment Features Learning: Adversarial Multi-task Learning for Aspect-based Sentiment Analysis

Contact Info

Product

Resources

About