# Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning

arXiv: https://arxiv.org/abs/1910.14192 · HTML: https://mlsanity.com/paper/1910.14192/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 22 of 22)

- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training](https://mlsanity.com/paper/2304.09563/) (2023)
- [QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction](https://mlsanity.com/paper/2108.08468/) (2021)
- [DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction](https://mlsanity.com/paper/2109.00571/) (2021)
- [A Unified One-Step Solution for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.04152/) (2023)
- [Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation](https://mlsanity.com/paper/2107.01598/) (2021)
- [Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.14898/) (2023)
- [HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression](https://mlsanity.com/paper/2110.08551/) (2021)
- [Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering](https://mlsanity.com/paper/2305.08655/) (2023)
- [Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2305.14434/) (2023)
- [Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering](https://mlsanity.com/paper/2211.08588/) (2022)
- [Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2305.09509/) (2023)
- [Table-Filling via Mean Teacher for Cross-domain Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2407.21052/) (2024)
- [A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2201.12549/) (2022)
- [Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2211.05457/) (2022)
- [Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction](https://mlsanity.com/paper/2302.14719/) (2023)
- [Inclusive FinTech Lending via Contrastive Learning and Domain Adaptation](https://mlsanity.com/paper/2305.05827/) (2023)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [An Empirical Study on Measuring the Similarity of Sentential Arguments with Language Model Domain Adaptation](https://mlsanity.com/paper/2102.09786/) (2021)
- [Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis](https://mlsanity.com/paper/2303.00815/) (2023)
- [An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2311.01713/) (2023)

## Abstract (arXiv)

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method.