Pseudo-Labels Are All You Need
This work addresses text complexity estimation for language learners, but it is incremental as it applies an existing pseudo-label method to a specific domain.
The paper tackled the problem of predicting text complexity for German learners using a pseudo-label-based approach, achieving impressive results without feature engineering or additional labeled data.
Automatically estimating the complexity of texts for readers has a variety of applications, such as recommending texts with an appropriate complexity level to language learners or supporting the evaluation of text simplification approaches. In this paper, we present our submission to the Text Complexity DE Challenge 2022, a regression task where the goal is to predict the complexity of a German sentence for German learners at level B. Our approach relies on more than 220,000 pseudo-labels created from the German Wikipedia and other corpora to train Transformer-based models, and refrains from any feature engineering or any additional, labeled data. We find that the pseudo-label-based approach gives impressive results yet requires little to no adjustment to the specific task and therefore could be easily adapted to other domains and tasks.