concept

question-answering systems

Facts (15)

Sources

Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Springer Apr 3, 2023 8 facts

referenceAI systems such as recommenders, question-answering systems, and information retrieval tools widely utilize knowledge graphs.

claimThe richness of information within knowledge graphs enhances the performance of AI systems like recommenders, question-answering systems, and information retrieval tools.

claimKnowledge graphs provide benefits to AI systems, specifically in the domains of recommender systems, question-answering systems, and information retrieval.

claimRecommender systems, question-answering systems, and information retrieval tools benefit from utilizing knowledge graphs because these graphs offer high-quality representations of domain knowledge.

referenceQuestion answering systems are central AI services that search for answers to natural language questions by analyzing semantic meanings, as noted by Dimitrakis et al. (2020) and Das et al. (2022).

claimTraditional question-answering systems match textual questions with answers in unstructured text databases by analyzing semantic relationships and matching questions to answers with maximum semantic similarity.

claimTraditional question-answering systems suffer from reduced efficiency because they must analyze an enormous search space when filtrating massive amounts of unstructured data.

referenceRecommender systems, question-answering systems, and information retrieval tools utilize knowledge graphs for input data and benefit significantly from them.

A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Springer Nov 4, 2024 2 facts

claimThe survey differentiates itself from previous literature by adopting a holistic perspective that covers a broad spectrum of integration techniques and architectures, rather than focusing on isolated technologies or narrow applications like semantic search or question-answering systems.

referenceSQuAD (Stanford Question Answering Dataset) is a benchmark that evaluates question-answering systems by requiring models to read and answer questions based on provided passages, measuring information retrieval and comprehension.

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv Sep 22, 2025 1 fact

claimGraph neural networks (GNNs) have been investigated as a technique to enhance retrieval coverage from passages in question-answering systems, as noted by Li et al. in 2025.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 1 fact

referenceHiroshi Honda and Masafumi Hagiwara developed question answering systems utilizing deep learning-based symbolic processing, as published in IEEE Access in 2019.

Combining large language models with enterprise knowledge graphs frontiersin.org Frontiers Aug 26, 2024 1 fact

claimCompanies utilize Knowledge Graphs to improve product performance, specifically by boosting data representation and transparency in recommendation systems, increasing efficiency in question-answering systems, and enhancing accuracy in information retrieval systems.

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 1 fact

claimKnowledge graphs serve as the backbone for various data science applications, including question-answering systems, recommendation systems, and the prediction of drug-target interactions.

HybridRAG: Integrating Knowledge Graphs and Vector Retrieval ... kargarisaac.medium.com Isaac Kargar · Medium Jan 9, 2025 1 fact

claimHybridRAG combines the strengths of VectorRAG and GraphRAG to enhance the performance of question-answering systems in financial contexts.