HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
It addresses inefficiencies in open-domain QA for users needing accurate answers from large text collections, though it is incremental as it builds on existing RC approaches.
The paper tackles open-domain question answering by addressing limitations of applying reading comprehension models, proposing a hierarchical probabilistic formulation and model (HAS-QA) that handles paragraphs without answers, multiple answer spans, and position dependencies, resulting in significant performance improvements over baselines on public datasets.
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.