# RankQA: Neural Question Answering with Answer Re-Ranking

## TL;DR

RankQA introduces a third answer re-ranking stage in neural question answering, effectively combining retrieval and comprehension features to improve accuracy, especially with varying corpus sizes, outperforming existing systems on multiple benchmarks.

## Contribution

The paper proposes a novel three-stage neural QA framework with answer re-ranking, enhancing performance and robustness over traditional two-stage methods.

## Key findings

- Outperforms complex QA systems on 3 out of 4 benchmarks.
- Effective in dynamic corpus size scenarios.
- Simple design enables efficient, data-sparse estimation.

## Abstract

The conventional paradigm in neural question answering (QA) for narrative content is limited to a two-stage process: first, relevant text passages are retrieved and, subsequently, a neural network for machine comprehension extracts the likeliest answer. However, both stages are largely isolated in the status quo and, hence, information from the two phases is never properly fused. In contrast, this work proposes RankQA: RankQA extends the conventional two-stage process in neural QA with a third stage that performs an additional answer re-ranking. The re-ranking leverages different features that are directly extracted from the QA pipeline, i.e., a combination of retrieval and comprehension features. While our intentionally simple design allows for an efficient, data-sparse estimation, it nevertheless outperforms more complex QA systems by a significant margin: in fact, RankQA achieves state-of-the-art performance on 3 out of 4 benchmark datasets. Furthermore, its performance is especially superior in settings where the size of the corpus is dynamic. Here the answer re-ranking provides an effective remedy against the underlying noise-information trade-off due to a variable corpus size. As a consequence, RankQA represents a novel, powerful, and thus challenging baseline for future research in content-based QA.