# Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure

arXiv: https://arxiv.org/abs/2211.07743 · HTML: https://mlsanity.com/paper/2211.07743/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [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)
- [Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training](https://mlsanity.com/paper/2111.02194/) (2021)
- [An Empirical Study on Neural Keyphrase Generation](https://mlsanity.com/paper/2009.10229/) (2020)
- [SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations](https://mlsanity.com/paper/2109.07424/) (2021)

## Built on by (most cited first, 13 of 13)

- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.00418/) (2023)
- [A Unified One-Step Solution for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.04152/) (2023)
- [BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2406.07365/) (2024)
- [iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples](https://mlsanity.com/paper/2311.03896/) (2023)
- [ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning](https://mlsanity.com/paper/2407.15341/) (2024)
- [Towards Semantic Integration of Opinions: Unified Opinion Concepts Ontology and Extraction Task](https://mlsanity.com/paper/2505.18703/) (2025)
- [Adaptive Data Augmentation for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2401.06394/) (2024)
- [ROAST: Review-level Opinion Aspect Sentiment Target Joint Detection for ABSA](https://mlsanity.com/paper/2405.20274/) (2024)
- [OATS: Opinion Aspect Target Sentiment Quadruple Extraction Dataset for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2309.13297/) (2023)
- [An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2311.01713/) (2023)
- [Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extraction](https://mlsanity.com/paper/2404.13751/) (2024)
- [Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples](https://mlsanity.com/paper/2505.10389/) (2025)

## Abstract (arXiv)

Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples. However, these models struggle with implicit sentiment expressions, which are commonly observed in opinionated content such as online reviews. In this work, we introduce GEN-SCL-NAT, which consists of two techniques for improved structured generation for ACOS quadruple extraction. First, we propose GEN-SCL, a supervised contrastive learning objective that aids quadruple prediction by encouraging the model to produce input representations that are discriminable across key input attributes, such as sentiment polarity and the existence of implicit opinions and aspects. Second, we introduce GEN-NAT, a new structured generation format that better adapts autoregressive encoder-decoder models to extract quadruples in a generative fashion. Experimental results show that GEN-SCL-NAT achieves top performance across three ACOS datasets, averaging 1.48% F1 improvement, with a maximum 1.73% increase on the LAPTOP-L1 dataset. Additionally, we see significant gains on implicit aspect and opinion splits that have been shown as challenging for existing ACOS approaches.