# Open Aspect Target Sentiment Classification with Natural Language Prompts

arXiv: https://arxiv.org/abs/2109.03685 · HTML: https://mlsanity.com/paper/2109.03685/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 8 Sep 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines](https://mlsanity.com/paper/2006.04884/) (2020)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification](https://mlsanity.com/paper/1908.11860/) (2019)
- [Unsupervised Question Answering by Cloze Translation](https://mlsanity.com/paper/1906.04980/) (2019)
- [GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2009.10557/) (2020)

## Built on by (most cited first, 20 of 20)

- [Toxicity Detection with Generative Prompt-based Inference](https://mlsanity.com/paper/2205.12390/) (2022)
- [Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning](https://mlsanity.com/paper/2212.01117/) (2022)
- [Fine-grained Affective Processing Capabilities Emerging from Large Language Models](https://mlsanity.com/paper/2309.01664/) (2023)
- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization](https://mlsanity.com/paper/2302.05574/) (2023)
- [A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2204.07832/) (2022)
- [Few-Shot Stance Detection via Target-Aware Prompt Distillation](https://mlsanity.com/paper/2206.13214/) (2022)
- [UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning](https://mlsanity.com/paper/2211.10986/) (2022)
- [A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2204.05356/) (2022)
- [Zero-Shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2202.01924/) (2022)
- [DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification](https://mlsanity.com/paper/2307.09813/) (2023)
- [MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning](https://mlsanity.com/paper/2304.09402/) (2023)
- [TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2305.10866/) (2023)
- [Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction](https://mlsanity.com/paper/2210.15843/) (2022)
- [Zero-shot Aspect-level Sentiment Classification via Explicit Utilization of Aspect-to-Document Sentiment Composition](https://mlsanity.com/paper/2209.02276/) (2022)
- [Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models](https://mlsanity.com/paper/2402.02145/) (2024)
- [Opinion Tree Parsing for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2306.08925/) (2023)
- [Exploiting Contextual Target Attributes for Target Sentiment Classification](https://mlsanity.com/paper/2312.13766/) (2023)
- [Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extraction](https://mlsanity.com/paper/2404.13751/) (2024)
- [Uncovering Agendas: A Novel French & English Dataset for Agenda Detection on Social Media](https://mlsanity.com/paper/2405.00821/) (2024)

## Abstract (arXiv)

For many business applications, we often seek to analyze sentiments associated with any arbitrary aspects of commercial products, despite having a very limited amount of labels or even without any labels at all. However, existing aspect target sentiment classification (ATSC) models are not trainable if annotated datasets are not available. Even with labeled data, they fall short of reaching satisfactory performance. To address this, we propose simple approaches that better solve ATSC with natural language prompts, enabling the task under zero-shot cases and enhancing supervised settings, especially for few-shot cases. Under the few-shot setting for SemEval 2014 Task 4 laptop domain, our method of reformulating ATSC as an NLI task outperforms supervised SOTA approaches by up to 24.13 accuracy points and 33.14 macro F1 points. Moreover, we demonstrate that our prompts could handle implicitly stated aspects as well: our models reach about 77% accuracy on detecting sentiments for aspect categories (e.g., food), which do not necessarily appear within the text, even though we trained the models only with explicitly mentioned aspect terms (e.g., fajitas) from just 16 reviews - while the accuracy of the no-prompt baseline is only around 65%.