UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

Anonymous

Abstract:

We study open-domain question answering with \emph{structured, unstructured} and \emph{semi-structured} knowledge sources, including text, tables, lists and knowledge bases.
Departing from prior work, we propose a unifying approach that homogenizes all sources by reducing them to text and applies the retriever-reader model which has so far been limited to text sources only.
Our approach greatly improves the results on knowledge-base QA tasks by 11 points, compared to latest graph-based methods.
More importantly, we demonstrate that our \emph{unified knowledge} (\uniqa{}) model is a simple and yet effective way to combine heterogeneous sources of knowledge, advancing the state-of-the-art results on two popular question answering benchmarks, NaturalQuestions and WebQuestions, by 3.5 and 2.6 points, respectively.