Zero and Few-shot Learning for Author Profiling
This addresses the problem of low-resource author profiling for researchers and practitioners, offering a more data-efficient method, though it is incremental as it builds on existing entailment techniques.
The paper tackled author profiling with minimal training data by exploring zero and few-shot models based on entailment, achieving 80% of the accuracy of previous approaches using less than 50% of the training data on average.
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.