Models for text generation have become focal for many research tasks and especially for the generation of sentence corpora.
Data balancing is a known technique for improving the performance of classification tasks.
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks.
We propose a method for end-to-end training of a base neural network that integrates calls to existing black-box functions.
At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application.