Knowledge Base Question Answering
46 papers with code • 5 benchmarks • 9 datasets
Knowledge Base Q&A is the task of answering questions from a knowledge base.
( Image credit: Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering )
Benchmarks
These leaderboards are used to track progress in Knowledge Base Question Answering
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
WebQuestionsSP
ComplexWebQuestions
FrenchMedMCQA
VANiLLa
Most implemented papers
Knowledge Base Question Answering by Case-based Reasoning over Subgraphs
Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed.
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
ruckbreasoning/subgraphretrievalkbqa
•
•
ACL 2022
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning.
ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering
dki-lab/arcaneqa
•
•
COLING 2022
Question answering on knowledge bases (KBQA) poses a unique challenge for semantic parsing research due to two intertwined challenges: large search space and ambiguities in schema linking.
Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment
tttttttty/alcqa
•
•
Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions.
Few-shot In-context Learning for Knowledge Base Question Answering
On GrailQA and WebQSP, our model is also on par with other fully-trained models.
SRTK: A Toolkit for Semantic-relevant Subgraph Retrieval
In this paper, we present SRTK, a user-friendly toolkit for semantic-relevant subgraph retrieval from large-scale knowledge graphs.
Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata
By pairing our semantic parser with GPT-3, we combine verifiable results with qualified GPT-3 guesses to provide useful answers to 96% of the questions in dev.
Knowledge Base Question Answering for Space Debris Queries
pauldrm/discosqa
•
•
In this work we present a system, developed for the European Space Agency (ESA), that can answer complex natural language queries, to support engineers in accessing the information contained in a KB that models the orbital space debris environment.
Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
cdhx/qdtqa
•
•
To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA.
FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users.
