Knowledge Tree
knowledge representation
Also known as: KR, knowledge representations
Facts (28)
Sources
Call for Papers: KR meets Machine Learning and Explanation kr.org 7 facts
perspectiveThe field of Knowledge Representation (KR) provides a repertoire of technologies for leveraging knowledge in both Machine Learning (ML) and explanation pipelines.
procedureThe KR 2026 special track 'KR meets Machine Learning and Explanation' mandates that all submissions must fall into the intersection of Knowledge Representation and either Machine Learning or explanation; papers that do not meet this criterion will be desk-rejected before the review process begins.
claimThe KR 2026 special track invites contributions that use Knowledge Representation (KR) methods to explain AI models, or that explain numeric and symbolic models themselves.
claimThe KR 2026 special track on 'KR meets Machine Learning and Explanation' aims to focus on the synergistic interactions between Knowledge Representation (KR) and the fields of Machine Learning (ML) and explanation.
claimThe KR 2026 special track invites contributions that use Knowledge Representation (KR) methods to solve Machine Learning (ML) challenges, use ML methods to solve KR challenges, or integrate learning and reasoning for better modeling, solving, or explaining tasks.
claimThe KR 2026 special track 'KR meets Machine Learning and Explanation' invites research on the intersection of Knowledge Representation and Machine Learning, specifically covering topics such as learning symbolic knowledge (ontologies, knowledge graphs, action theories), KR-driven plan computation, logic-based learning, neural-symbolic learning, statistical relational learning, symbolic reinforcement learning, and the mutual use of KR techniques and LLMs.
claimThe KR 2026 special track welcomes papers focusing on evaluation protocols and benchmarking of hybrid solutions that combine Knowledge Representation (KR) with Machine Learning (ML) or explanation.
Call for Papers: Main Track - KR 2026 kr.org 3 facts
claimThe KR 2026 conference welcomes papers from other areas that demonstrate clear use of, or contributions to, the principles or practice of Knowledge Representation, as well as reports from the field regarding applications, experiments, developments, and tests.
claimThe KR 2026 conference solicits papers presenting novel results on the principles of Knowledge Representation (KR) that contribute to the formal foundations of the field or demonstrate the applicability of KR techniques to implemented or implementable systems.
claimThe KR 2026 conference accepts submissions on topics including argumentation, belief change, common-sense reasoning, computational aspects of knowledge representation, description logics, ethical considerations in KR, explanation/abduction/diagnosis, geometric/spatial/temporal reasoning, inconsistency- and exception-tolerant reasoning, knowledge acquisition, knowledge compilation/automated reasoning/satisfiability/model counting, knowledge representation languages, logic programming/answer set programming, model learning for diagnosis and planning, modeling and reasoning about preferences, modeling constraints and constraint solving, multi- and order-sorted representations and reasoning, non-monotonic logics, ontologies and knowledge-enriched data management, philosophical foundations of KR, qualitative reasoning, reasoning about actions and change/action languages, reasoning about knowledge/beliefs/mental attitudes, reasoning in knowledge graphs, reasoning in multi-agent systems, semantic web, similarity-based and contextual reasoning, and uncertainty and vagueness.
Call for Papers: Special Session on KR and Machine Learning kr.org 3 facts
procedureSubmissions to the Special Session on KR and Machine Learning are peer-reviewed by Program Committee members who are active in both Knowledge Representation and Machine Learning fields.
claimThe Special Session on KR and Machine Learning at KR2022 invites submissions that integrate knowledge representation (KR) and machine learning (ML), specifically focusing on using KR methods to solve ML challenges (such as knowledge-guided or explainable learning), using ML methods to solve KR challenges (such as efficient inference or knowledge base completion), integrating learning and reasoning, and applying combined approaches to real-world problems.
claimThe Special Session on KR and Machine Learning requires submissions to be at the intersection of Knowledge Representation and Machine Learning, meaning submissions focused exclusively on either KR or ML will not be accepted.
A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Nov 4, 2024 2 facts
accountThe authors conducted a systematic literature review of NLP, machine learning, and knowledge representation research from the last decade to understand approaches for integrating knowledge graphs (KGs) and large language models (LLMs).
claimFuture evaluation techniques for integrated knowledge graph and LLM systems should aim to measure complex aspects such as knowledge representation and reasoning capabilities, rather than relying solely on traditional performance metrics.
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org Jul 11, 2024 2 facts
referenceRonald Brachman and Hector Levesque authored a foundational text on knowledge representation and reasoning.
claimAllen Newell and Herbert A. Simon created the Logic Theorist in 1956, a system that gained prominence for symbolic AI by using high-level knowledge representations and symbolic manipulation to mimic human reasoning.
Papers - Dr Vaishak Belle vaishakbelle.github.io 2 facts
referenceI. Mocanu and Vaishak Belle authored 'Knowledge representation and acquisition in the era of large language models: Reflections on learning to reason via PAC-Semantics', published in the Natural Language Processing Journal in 2023.
referenceThe paper 'Knowledge Representation and Acquisition for Ethical AI: Challenges and Opportunities' by V. Belle was published in Ethics and Information Technology in 2023.
Knowledge Graph Combined with Retrieval-Augmented Generation ... drpress.org Dec 2, 2025 1 fact
claimIntegrating Knowledge Graphs (KGs) with Retrieval-Augmented Generation (RAG) enhances the knowledge representation and reasoning abilities of Large Language Models (LLMs) by utilizing structured knowledge, which enables the generation of more accurate answers.
How to combine LLMs and Knowledge Graphs for enterprise AI linkedin.com Nov 14, 2025 1 fact
claimOntologies assist AI systems in the representation of knowledge.
A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Dec 9, 2025 1 fact
claimThe goal of neuro-symbolic AI is to unify neural networks and symbolic AI to combine the inductive learning capacity of neural networks—which excels at discovering latent patterns from unstructured or noisy data—with the explicit knowledge representations of symbolic AI, which enable interpretability, rule-based reasoning, and systematic extension to new tasks.
Building Better Agentic Systems with Neuro-Symbolic AI cutter.com Dec 10, 2025 1 fact
claimSymbolic systems provide structured logic, interpretability, and explicit knowledge representation.
Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org 1 fact
claimThe construction of a knowledge graph is a multi-disciplinary effort that requires expertise from natural language processing, data integration, knowledge representation, and knowledge management.
Neuro-symbolic AI - Wikipedia en.wikipedia.org 1 fact
claimNeuro-symbolic AI is a subfield of artificial intelligence that integrates neural methods, such as neural networks and deep learning, with symbolic methods, such as formal logic, knowledge representation, and automated reasoning.
The State Of The Art On Knowledge Graph Construction From Text nlpsummit.org 1 fact
claimNandana Mihindukulasooriya's research interests include relation extraction and linking, information extraction, knowledge representation and reasoning, and Neuro-Symbolic AI.
Construction of intelligent decision support systems through ... - Nature nature.com Oct 10, 2025 1 fact
claimThe framework proposed in the Nature article encourages a nexus between knowledge representation and natural language inference.
Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org 1 fact
referenceThe paper 'Pretrain-kge: learning knowledge representation from pretrained language models' was published in the Findings of the Association for Computational Linguistics: EMNLP 2020.