# iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples

arXiv: https://arxiv.org/abs/2311.03896 · HTML: https://mlsanity.com/paper/2311.03896/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 7 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [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)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Learning to Branch for Multi-Task Learning](https://mlsanity.com/paper/2006.01895/) (2020)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [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)
- [A Unified Model for Opinion Target Extraction and Target Sentiment Prediction](https://mlsanity.com/paper/1811.05082/) (2018)
- [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1906.06906/) (2019)
- [Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision](https://mlsanity.com/paper/1907.03750/) (2019)
- [CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis](https://mlsanity.com/paper/1812.10735/) (2018)
- [Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure](https://mlsanity.com/paper/2211.07743/) (2022)
- [A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2204.12674/) (2022)
- [Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.00418/) (2023)
- [Extreme Classification via Adversarial Softmax Approximation](https://mlsanity.com/paper/2002.06298/) (2020)
- [UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning](https://mlsanity.com/paper/2211.10986/) (2022)
- [A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis](https://mlsanity.com/paper/2010.02784/) (2020)
- [A Tale of Two Efficient and Informative Negative Sampling Distributions](https://mlsanity.com/paper/2012.15843/) (2020)

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

- [EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks](https://mlsanity.com/paper/2508.17008/) (2025)
- [Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis](https://mlsanity.com/paper/2605.20998/) (2026)

## Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) have been extensively studied, but little light has been shed on the quadruple extraction consisting of four fundamental elements: aspects, categories, opinions and sentiments, especially with implicit aspects and opinions. In this paper, we propose a new method iACOS for extracting Implicit Aspects with Categories and Opinions with Sentiments. First, iACOS appends two implicit tokens at the end of a text to capture the context-aware representation of all tokens including implicit aspects and opinions. Second, iACOS develops a sequence labeling model over the context-aware token representation to co-extract explicit and implicit aspects and opinions. Third, iACOS devises a multi-label classifier with a specialized multi-head attention for discovering aspect-opinion pairs and predicting their categories and sentiments simultaneously. Fourth, iACOS leverages informative and adaptive negative examples to jointly train the multi-label classifier and the other two classifiers on categories and sentiments by multi-task learning. Finally, the experimental results show that iACOS significantly outperforms other quadruple extraction baselines according to the F1 score on two public benchmark datasets.