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 )

Relation-Aware Question Answering for Heterogeneous Knowledge Graphs

yanmenxue/rah-kbqa 19 Dec 2023

To address this issue, we construct a \textbf{dual relation graph} where each node denotes a relation in the original KG (\textbf{primal entity graph}) and edges are constructed between relations sharing same head or tail entities.

5
19 Dec 2023

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

lhrlab/chatkbqa 13 Oct 2023

Knowledge Base Question Answering (KBQA) aims to derive answers to natural language questions over large-scale knowledge bases (KBs), which are generally divided into two research components: knowledge retrieval and semantic parsing.

175
13 Oct 2023

Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases

yhshu/distribution-shifts-for-kbqa 15 Sep 2023

Language models (LMs) have already demonstrated remarkable abilities in understanding and generating both natural and formal language.

2
15 Sep 2023

Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA

dongguanting/skp-for-kbqa 28 Aug 2023

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs.

17
28 Aug 2023

FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering

leezythu/flexkbqa 23 Aug 2023

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.

51
23 Aug 2023

Question Decomposition Tree for Answering Complex Questions over Knowledge Bases

cdhx/qdtqa 13 Jun 2023

To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA.

10
13 Jun 2023

Knowledge Base Question Answering for Space Debris Queries

pauldrm/discosqa 31 May 2023

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.

3
31 May 2023

Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata

stanford-oval/wikidata-emnlp23 23 May 2023

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.

65
23 May 2023

SRTK: A Toolkit for Semantic-relevant Subgraph Retrieval

happen2me/subgraph-retrieval-toolkit 6 May 2023

In this paper, we present SRTK, a user-friendly toolkit for semantic-relevant subgraph retrieval from large-scale knowledge graphs.

11
06 May 2023

Few-shot In-context Learning for Knowledge Base Question Answering

ltl3a87/kb-binder 2 May 2023

On GrailQA and WebQSP, our model is also on par with other fully-trained models.

51
02 May 2023