# Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysis

arXiv: https://arxiv.org/abs/2309.15476 · HTML: https://mlsanity.com/paper/2309.15476/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Span-based Joint Entity and Relation Extraction with Transformer Pre-training](https://mlsanity.com/paper/1909.07755/) (2019)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [Stance Detection with Bidirectional Conditional Encoding](https://mlsanity.com/paper/1606.05464/) (2016)
- [DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization](https://mlsanity.com/paper/2109.02492/) (2021)
- [Poolingformer: Long Document Modeling with Pooling Attention](https://mlsanity.com/paper/2105.04371/) (2021)
- [Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2107.12214/) (2021)
- [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021)
- [DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2211.05705/) (2022)
- [Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction](https://mlsanity.com/paper/2010.04640/) (2020)
- [Improving Document-Level Sentiment Analysis with User and Product Context](https://mlsanity.com/paper/2011.09210/) (2020)

## Built on by (most cited first, 4 of 4)

- [SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents](https://mlsanity.com/paper/2502.15538/) (2025)
- [Adaptive Data Augmentation for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2401.06394/) (2024)
- [Dialogues Aspect-based Sentiment Quadruple Extraction via Structural Entropy Minimization Partitioning](https://mlsanity.com/paper/2508.05023/) (2025)
- [TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis](https://mlsanity.com/paper/2605.01717/) (2026)

## Abstract (arXiv)

Conversational aspect-based sentiment quadruple analysis (DiaASQ) aims to extract the quadruple of target-aspect-opinion-sentiment within a dialogue. In DiaASQ, a quadruple's elements often cross multiple utterances. This situation complicates the extraction process, emphasizing the need for an adequate understanding of conversational context and interactions. However, existing work independently encodes each utterance, thereby struggling to capture long-range conversational context and overlooking the deep inter-utterance dependencies. In this work, we propose a novel Dynamic Multi-scale Context Aggregation network (DMCA) to address the challenges. Specifically, we first utilize dialogue structure to generate multi-scale utterance windows for capturing rich contextual information. After that, we design a Dynamic Hierarchical Aggregation module (DHA) to integrate progressive cues between them. In addition, we form a multi-stage loss strategy to improve model performance and generalization ability. Extensive experimental results show that the DMCA model outperforms baselines significantly and achieves state-of-the-art performance.