UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
This work provides a simpler and more effective way to combine heterogeneous knowledge sources for open-domain question answering, which is beneficial for researchers and practitioners working on complex QA systems.
This paper addresses open-domain question answering by unifying structured, unstructured, and semi-structured knowledge sources into a text-based representation. This approach significantly improves results on knowledge-base QA tasks by 11 points and advances state-of-the-art on NaturalQuestions and WebQuestions benchmarks by 3.5 and 2.6 points, respectively.
We study open-domain question answering with structured, unstructured and 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 unified knowledge (UniK-QA) 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. The code of UniK-QA is available at: https://github.com/facebookresearch/UniK-QA.