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

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.

PDF Abstract Findings (NAACL) 2022 PDF Findings (NAACL) 2022 Abstract

Results from the Paper

 Ranked #1 on Open-Domain Question Answering on WebQuestions (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Open-Domain Question Answering Natural Questions UniK-QA Exact Match 54.9 # 3
Question Answering Natural Questions (long) UniK-QA EM 54.9 # 4
Open-Domain Question Answering TQA UniK-QA Exact Match 65.5 # 1
Open-Domain Question Answering WebQuestions UniK-QA Exact Match 57.7 # 1
Knowledge Base Question Answering WebQuestionsSP UniK-QA (T5-large) Hits@1 79.1 # 3
Knowledge Base Question Answering WebQuestionsSP UniK-QA (T5-base) Hits@1 76.7 # 4


No methods listed for this paper. Add relevant methods here