UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/facebookresearch/UniK-QAOfficialIn papernone★ 50
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Natural Questions | UniK-QA | Exact Match | 54.9 | — | Unverified |
| TQA | UniK-QA | Exact Match | 65.5 | — | Unverified |
| WebQuestions | UniK-QA | Exact Match | 57.7 | — | Unverified |