In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals.
Recently, much attention has been paid to the societal impact of AI, especially concerns regarding its fairness.
In this paper, we propose a posterior regularization framework for the variational approach to the weakly supervised sentiment analysis to better control the posterior distribution of the label assignment.
A growing proportion of human interactions are digitized on social media platforms and subjected to algorithmic decision-making, and it has become increasingly important to ensure fair treatment from these algorithms.
Our objective function is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment classifier.
These word pairs can be extracted by using dependency parsers and simple rules.