Unsupervised and weakly supervised approaches for answer selection tasks with scarce annotations

Addressing Answer Selection (AS) tasks with complex neural networks typically requires a large amount of annotated data to increase the accuracy of the models. In this work, we are interested in simple models that can potentially give good performance on datasets with no or few annotations. First, we propose new unsupervised baselines that leverage distributed word and sentence representations. Second, we compare the ability of our neural architectures to learn from few annotated examples in a weakly supervised scheme and we demonstrate how these methods can benefit from a pre-training on an external dataset. With an emphasis on results reproducibility, we show that our simple methods can reach or approach state-of-the-art performances on four common AS datasets.