Author profiling classifies author characteristics by analyzing how language is shared among people. In this work, we study that task from a low-resource viewpoint: using little or no training data. We explore different zero and few-shot models based on entailment and evaluate our systems on several profiling tasks in Spanish and English. In addition, we study the effect of both the entailment hypothesis and the size of the few-shot training sample. We find that entailment-based models out-perform supervised text classifiers based on roberta-XLM and that we can reach 80% of the accuracy of previous approaches using less than 50\% of the training data on average.
@article{arxiv.2204.10543,
title = {Zero and Few-shot Learning for Author Profiling},
author = {Mara Chinea-Rios and Thomas Müller and Gretel Liz De la Peña Sarracén and Francisco Rangel and Marc Franco-Salvador},
journal= {arXiv preprint arXiv:2204.10543},
year = {2022}
}