# CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis

arXiv: https://arxiv.org/abs/1812.10735 · HTML: https://mlsanity.com/paper/1812.10735/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2018.

## Built on by (most cited first, 21 of 21)

- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2103.07665/) (2021)
- [Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation](https://mlsanity.com/paper/2210.10291/) (2022)
- [Solving Aspect Category Sentiment Analysis as a Text Generation Task](https://mlsanity.com/paper/2110.07310/) (2021)
- [ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction](https://mlsanity.com/paper/2103.06605/) (2021)
- [A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2204.07832/) (2022)
- [A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2204.12674/) (2022)
- [Multi-Label Few-Shot Learning for Aspect Category Detection](https://mlsanity.com/paper/2105.14174/) (2021)
- [BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2204.03117/) (2022)
- [Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.00418/) (2023)
- [Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection](https://mlsanity.com/paper/2206.13980/) (2022)
- [The Limits of ChatGPT in Extracting Aspect-Category-Opinion-Sentiment Quadruples: A Comparative Analysis](https://mlsanity.com/paper/2310.06502/) (2023)
- [Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2110.02334/) (2021)
- [Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection](https://mlsanity.com/paper/2210.04220/) (2022)
- [MACSA: A Multimodal Aspect-Category Sentiment Analysis Dataset with Multimodal Fine-grained Aligned Annotations](https://mlsanity.com/paper/2206.13969/) (2022)
- [iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples](https://mlsanity.com/paper/2311.03896/) (2023)
- [Aspect-based Sentiment Analysis through EDU-level Attentions](https://mlsanity.com/paper/2202.02535/) (2022)
- [Opinion Tree Parsing for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2306.08925/) (2023)
- [S2GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2406.02902/) (2024)
- [KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering](https://mlsanity.com/paper/2407.00342/) (2024)

## Abstract (arXiv)

Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating aspect-specific sentence representations. However, the attention may inherently introduce noise and downgrade the performance. In this paper, we propose constrained attention networks (CAN), a simple yet effective solution, to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism. Specifically, we introduce orthogonal regularization on multiple aspects and sparse regularization on each single aspect. Experimental results on two public datasets demonstrate the effectiveness of our approach. We further extend our approach to multi-task settings and outperform the state-of-the-art methods.