# Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model

arXiv: https://arxiv.org/abs/2111.09634 · HTML: https://mlsanity.com/paper/2111.09634/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 18 Nov 2021.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Semantics-aware BERT for Language Understanding](https://mlsanity.com/paper/1909.02209/) (2019)
- [Entity-Relation Extraction as Multi-Turn Question Answering](https://mlsanity.com/paper/1905.05529/) (2019)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders](https://mlsanity.com/paper/2010.03851/) (2020)
- [Retrospective Reader for Machine Reading Comprehension](https://mlsanity.com/paper/2001.09694/) (2020)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1906.06906/) (2019)
- [Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification](https://mlsanity.com/paper/1906.03820/) (2019)
- [Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model](https://mlsanity.com/paper/1810.12836/) (2018)
- [Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction](https://mlsanity.com/paper/1805.04601/) (2018)
- [Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2103.07665/) (2021)
- [A Multi-task Learning Framework for Opinion Triplet Extraction](https://mlsanity.com/paper/2010.01512/) (2020)
- [Dependency or Span, End-to-End Uniform Semantic Role Labeling](https://mlsanity.com/paper/1901.05280/) (2019)
- [Fast and Effective Biomedical Entity Linking Using a Dual Encoder](https://mlsanity.com/paper/2103.05028/) (2021)
- [A Benchmark Study on Sentiment Analysis for Software Engineering Research](https://mlsanity.com/paper/1803.06525/) (2018)
- [A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?](https://mlsanity.com/paper/1808.03815/) (2018)
- [Text Compression-aided Transformer Encoding](https://mlsanity.com/paper/2102.05951/) (2021)
- [First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2102.08549/) (2021)
- [Syntax Role for Neural Semantic Role Labeling](https://mlsanity.com/paper/2009.05737/) (2020)
- [Grammatical Error Correction as GAN-like Sequence Labeling](https://mlsanity.com/paper/2105.14209/) (2021)
- [Learning Explicit and Implicit Structures for Targeted Sentiment Analysis](https://mlsanity.com/paper/1909.07593/) (2019)

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

- [FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction](https://mlsanity.com/paper/2306.14913/) (2023)
- [MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2406.11234/) (2024)
- [A semantically enhanced dual encoder for aspect sentiment triplet extraction](https://mlsanity.com/paper/2306.08373/) (2023)
- [A Better Choice: Entire-space Datasets for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2212.09052/) (2022)
- [Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning](https://mlsanity.com/paper/2403.07342/) (2024)
- [Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models](https://mlsanity.com/paper/2505.19631/) (2025)
- [Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2208.09617/) (2022)
- [Understanding Emotion Valence is a Joint Deep Learning Task](https://mlsanity.com/paper/2305.17422/) (2023)
- [Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding](https://mlsanity.com/paper/2501.07329/) (2025)
- [Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2502.01942/) (2025)
- [T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2505.05271/) (2025)
- [DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2606.01323/) (2026)
- [The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2607.03414/) (2026)

## Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources and reduce the error propagation in the pipeline. However, most of the existing joint models only focus on the benefits of encoder sharing between subtasks but ignore the difference. Therefore, we propose a joint ABSA model, which not only enjoys the benefits of encoder sharing but also focuses on the difference to improve the effectiveness of the model. In detail, we introduce a dual-encoder design, in which a pair encoder especially focuses on candidate aspect-opinion pair classification, and the original encoder keeps attention on sequence labeling. Empirical results show that our proposed model shows robustness and significantly outperforms the previous state-of-the-art on four benchmark datasets.