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

By Barlas Oğuz, Xilun Chen, Vladimir Karpukhin, Stanislav Peshterliev, Dmytro Okhonko, Michael Sejr Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih. 2020

106 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Question Answering & Reading Comprehension

In Knowledge Graphs & Representation

Citations in the corpus

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, methodology): “Structured knowledge encoding methods have been explored in many prior studies (Bogin et al., 2019; Lin et al., 2019; Yin et al., 2020a; Herzig et al., 2020; Agarwal et al., 2020; Saxena et al., 2020; Yasunaga and Liang, 2020; Yasunaga et al., 2021; Oguz et al., 2021).”
TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021, background): “It is worth noting that for semi-structured tables, the answer may not be exactly table cell values, but their normalized forms (e.g., from 2k to 2,000 ), which makes downstream tasks more challenging (Oguz et al., 2020).”
Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “UniK-QA [143] concatenates the text forms of the components in a triplet and build document pool for retrieval.”
StructGPT: A General Framework for Large Language Model to Reason over Structured Data (2023, methodology): “An intuitive idea is to conduct a two-stage procedure as prior studies on retrieval-augmented approaches (Izacard et al., 2022; Oguz et al., 2022), in which LLMs are employed to first collect sufficient evidence relating to the question and then figure out the answer by the LLMs.”
A Unified Encoder-Decoder Framework with Entity Memory (2022, background): “A popular approach to incorporate knowledge into the generation process is retrieving evidence documents from external sources (Lewis et al., 2020b; Izacard and 2021; Oguz et al., 2020; Yu et al., 2022c).”