# A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

arXiv: https://arxiv.org/abs/2208.11283 · HTML: https://mlsanity.com/paper/2208.11283/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [A Mutual Information Maximization Perspective of Language Representation Learning](https://mlsanity.com/paper/1910.08350/) (2019)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification](https://mlsanity.com/paper/1906.03820/) (2019)
- [Adversarial Training for Aspect-Based Sentiment Analysis with BERT](https://mlsanity.com/paper/2001.11316/) (2020)
- [Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks](https://mlsanity.com/paper/1804.06536/) (2018)
- [DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction](https://mlsanity.com/paper/1906.01794/) (2019)
- [Aspect-Based Sentiment Analysis Using a Two-Step Neural Network Architecture](https://mlsanity.com/paper/1709.06311/) (2017)

## Built on by (most cited first, 3 of 3)

- [Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer](https://mlsanity.com/paper/2404.13640/) (2024)
- [ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework](https://mlsanity.com/paper/2409.10289/) (2024)
- [FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis](https://mlsanity.com/paper/2505.21040/) (2025)

## Abstract (arXiv)

Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification). However, most existing approaches either sequentially extract task-specific features, leading to insufficient feature interactions, or they encode aspect features and sentiment features in a parallel manner, implying that feature representation in each task is largely independent of each other except for input sharing. Both of them ignore the internal correlations between the aspect extraction and sentiment classification. To solve this problem, we novelly propose a hierarchical interactive network (HI-ASA) to model two-way interactions between two tasks appropriately, where the hierarchical interactions involve two steps: shallow-level interaction and deep-level interaction. First, we utilize cross-stitch mechanism to combine the different task-specific features selectively as the input to ensure proper two-way interactions. Second, the mutual information technique is applied to mutually constrain learning between two tasks in the output layer, thus the aspect input and the sentiment input are capable of encoding features of the other task via backpropagation. Extensive experiments on three real-world datasets demonstrate HI-ASA's superiority over baselines.