Meta-based Self-training and Re-weighting for Aspect-based Sentiment Analysis

[Meta-based Self-training and Re-weighting for Aspect-based Sentiment Analysis](https://ieeexplore.ieee.org/iel7/5165369/5520654/09870538.pdf)

I read this paper (Not completely, all except the methodology)

It is not a good one to write the summary because it is not related to my work on an **unsupervised** method for **latent** aspect detection.
However, as a record of reading this paper, the proposed method in this paper is a self-supervised one for multi-task to mitigate the problem of insufficient and imbalanced data in the Aspect-based Sentiment Analysis (ABSA). It consists of three models (teacher model, student model, and meta-weighter). The teacher model helps the student model to train with generating the labels and the meta-weighter will try to find the optimum weight for each label. There is an example of the ABSA task below:

**Input**
Opinion: "The restaurant is crowded but with efficient and accurate service."

**Output**

1.
- Aspect extraction: restaurant
- Opinion extraction: crowded
- Aspect-level sentiment classification: negative
-
2.
- Aspect extraction: service
- Opinion extraction: efficient
- Aspect-level sentiment classification: positive