# PGSO: Prompt-based Generative Sequence Optimization Network for Aspect-based Sentiment Analysis

arXiv: https://arxiv.org/abs/2412.00763 · HTML: https://mlsanity.com/paper/2412.00763/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 1 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2107.12214/) (2021)
- [Exploiting BERT for End-to-End Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1910.00883/) (2019)
- [A Unified Model for Opinion Target Extraction and Target Sentiment Prediction](https://mlsanity.com/paper/1811.05082/) (2018)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model](https://mlsanity.com/paper/2304.06248/) (2023)
- [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)
- [DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction](https://mlsanity.com/paper/1906.01794/) (2019)
- [A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2204.12674/) (2022)
- [BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2204.03117/) (2022)
- [SynGen: A Syntactic Plug-and-play Module for Generative Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2302.13032/) (2023)
- [RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2311.04467/) (2023)

## Built on by (most cited first, 2 of 2)

- [Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation](https://mlsanity.com/paper/2504.12331/) (2025)
- [From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning](https://mlsanity.com/paper/2604.13398/) (2026)

## Abstract (arXiv)

Recently, generative pre-training based models have demonstrated remarkable results on Aspect-based Sentiment Analysis (ABSA) task. However, previous works overemphasize crafting various templates to paraphrase training targets for enhanced decoding, ignoring the internal optimizations on generative models. Despite notable results achieved by these target-oriented optimization methods, they struggle with the complicated long texts since the implicit long-distance relation, e.g., aspect-opinion relation, is difficult to extract under the position embedding mechanism in generative models. Thus, in this paper, we first clarify the causes of the problem and introduce two sequence optimization strategies: the rule-based static optimization and the score-based dynamic optimization. The rule-based approach relies on handcraft priority of dependency relation to reorder the context, while the score-based algorithm dynamically regulates the contextual sequence by calculating word position scores using neural network. Based on the dynamic optimization structure, we further propose a unified Prompt-based Generative Sequence Optimization network (named PGSO), which jointly optimizes the training target as well as the generative model. Specifically, PGSO contains two components, namely, prompt construction and sequence regulator. The former constructs a task-specific prompt based on unsupervised training objects to fully utilize the pre-trained model. The latter jointly leverages semantic, syntactic and original-sequence information to dynamically regulate contextual sequence. Our experiments conducted on four ABSA tasks across multiple benchmarks indicate that PGSO outperforms state-of-the-art methods, with an average improvement of 3.52% in F1 score.