# HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering

arXiv: https://arxiv.org/abs/1901.03866 · HTML: https://mlsanity.com/paper/1901.03866/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2019.

## Built on by (most cited first, 8 of 8)

- [Natural Language Video Localization: A Revisit in Span-based Question Answering Framework](https://mlsanity.com/paper/2102.13558/) (2021)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [Why Machine Reading Comprehension Models Learn Shortcuts?](https://mlsanity.com/paper/2106.01024/) (2021)
- [Adaptive Information Seeking for Open-Domain Question Answering](https://mlsanity.com/paper/2109.06747/) (2021)
- [RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content](https://mlsanity.com/paper/2406.11811/) (2024)
- [Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding](https://mlsanity.com/paper/2301.03765/) (2023)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)
- [A Dataset of Open-Domain Question Answering with Multiple-Span Answers](https://mlsanity.com/paper/2402.09923/) (2024)

## Abstract (arXiv)

This paper is concerned with open-domain question answering (i.e., OpenQA). Recently, some works have viewed this problem as a reading comprehension (RC) task, and directly applied successful RC models to it. However, the performances of such models are not so good as that in the RC task. In our opinion, the perspective of RC ignores three characteristics in OpenQA task: 1) many paragraphs without the answer span are included in the data collection; 2) multiple answer spans may exist within one given paragraph; 3) the end position of an answer span is dependent with the start position. In this paper, we first propose a new probabilistic formulation of OpenQA, based on a three-level hierarchical structure, i.e.,~the question level, the paragraph level and the answer span level. Then a Hierarchical Answer Spans Model (HAS-QA) is designed to capture each probability. HAS-QA has the ability to tackle the above three problems, and experiments on public OpenQA datasets show that it significantly outperforms traditional RC baselines and recent OpenQA baselines.