# Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer

arXiv: https://arxiv.org/abs/1810.10437 · HTML: https://mlsanity.com/paper/1810.10437/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning](https://mlsanity.com/paper/2205.10857/) (2022)
- [Learning Speaker-specific Lip-to-Speech Generation](https://mlsanity.com/paper/2206.02050/) (2022)
- [Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction](https://mlsanity.com/paper/2208.08280/) (2022)
- [Retrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2210.15377/) (2022)
- [Tampered VAE for Improved Satellite Image Time Series Classification](https://mlsanity.com/paper/2203.16149/) (2022)

## Abstract (arXiv)

Aspect-term sentiment analysis (ATSA) is a longstanding challenge in natural language understanding. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborious and time-consuming, the amount of labeled data is limited for supervised learning. This paper proposes a semi-supervised method for the ATSA problem by using the Variational Autoencoder based on Transformer (VAET), which models the latent distribution via variational inference. By disentangling the latent representation into the aspect-specific sentiment and the lexical context, our method induces the underlying sentiment prediction for the unlabeled data, which then benefits the ATSA classifier. Our method is classifier agnostic, i.e., the classifier is an independent module and various advanced supervised models can be integrated. Experimental results are obtained on the SemEval 2014 task 4 and show that our method is effective with four classical classifiers. The proposed method outperforms two general semisupervised methods and achieves state-of-the-art performance.