Comparative Analysis of Neural QA models on SQuAD
This work provides insights for researchers in natural language processing by analyzing existing models on a standard benchmark, but it is incremental as it focuses on comparison rather than introducing new methods.
The paper tackled the problem of understanding and comparing neural question answering models on the SQuAD dataset, finding that prediction errors reveal model-specific biases through quantitative and qualitative analysis.
The task of Question Answering has gained prominence in the past few decades for testing the ability of machines to understand natural language. Large datasets for Machine Reading have led to the development of neural models that cater to deeper language understanding compared to information retrieval tasks. Different components in these neural architectures are intended to tackle different challenges. As a first step towards achieving generalization across multiple domains, we attempt to understand and compare the peculiarities of existing end-to-end neural models on the Stanford Question Answering Dataset (SQuAD) by performing quantitative as well as qualitative analysis of the results attained by each of them. We observed that prediction errors reflect certain model-specific biases, which we further discuss in this paper.