# RankQA: Neural Question Answering with Answer Re-Ranking

arXiv: https://arxiv.org/abs/1906.03008 · HTML: https://mlsanity.com/paper/1906.03008/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

## Built on by (most cited first, 15 of 15)

- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization](https://mlsanity.com/paper/2203.06569/) (2022)
- [Contrastive Domain Adaptation for Question Answering using Limited Text Corpora](https://mlsanity.com/paper/2108.13854/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Check It Again: Progressive Visual Question Answering via Visual Entailment](https://mlsanity.com/paper/2106.04605/) (2021)
- [CPopQA: Ranking Cultural Concept Popularity by LLMs](https://mlsanity.com/paper/2311.07897/) (2023)
- [Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer](https://mlsanity.com/paper/2311.06720/) (2023)
- [Towards Confident Machine Reading Comprehension](https://mlsanity.com/paper/2101.07942/) (2021)
- [Model Agnostic Answer Reranking System for Adversarial Question Answering](https://mlsanity.com/paper/2102.03016/) (2021)
- [QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation](https://mlsanity.com/paper/2210.10861/) (2022)
- [DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification](https://mlsanity.com/paper/2412.00600/) (2024)
- [Where Was COVID-19 First Discovered? Designing a Question-Answering System for Pandemic Situations](https://mlsanity.com/paper/2204.08787/) (2022)
- [Answer Consolidation: Formulation and Benchmarking](https://mlsanity.com/paper/2205.00042/) (2022)
- [Zero-shot Task Transfer for Invoice Extraction via Class-aware QA Ensemble](https://mlsanity.com/paper/2108.06069/) (2021)
- [DomainInv: Domain Invariant Fine Tuning and Adversarial Label Correction For QA Domain Adaptation](https://mlsanity.com/paper/2305.05589/) (2023)

## Abstract (arXiv)

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.