Knowledge Graphs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 4
- 보존된 평가 기록
- 19
A knowledge graph is a structured representation of information that organizes data into nodes (entities) and edges (relationships) to show how different pieces of knowledge are interconnected. It enables enhanced data integration, search, and inference by modeling the relationships between concepts and entities in a graph format.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/facebookresearch/head-to-tail
공식 코드https://github.com/fanourakis/experimental-review-ea
공식 코드Knowledge Graph Embedding Methods for Entity Alignment: An Experimental Review
https://github.com/fcihraeipnusnacwh/mrc-ce
공식 코드Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension
https://github.com/feiwangyuzhou/ternarycl
공식 코드Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning
https://github.com/fploetzky/websci2024
공식 코드Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs
https://github.com/francesco-sovrano/from-philosophy-to-interfaces-an-explanatory-method-and-a-tool-inspired-by-achinstein-s-theory-of-e
공식 코드https://github.com/francesco-sovrano/yai4hu
공식 코드https://github.com/francescoferrini/multirelationalgnn
공식 코드Meta-Path Learning for Multi-relational Graph Neural Networks
https://github.com/francoisluus/KGReasoning
공식 코드https://github.com/freesunshine0316/nary-grn
공식 코드Tackling Graphical NLP problems with Graph Recurrent Networks
https://github.com/fudandisc/disc-medllm
공식 코드DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
https://github.com/fusion-jena/automatic-kg-creation-with-llm
공식 코드https://github.com/futureeeeee/dynamic-rag
공식 코드https://github.com/gasolsun36/tog
공식 코드Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
https://github.com/gblackout/TILR
공식 코드https://github.com/ge-semtk/semtk
공식 코드SemTK: An Ontology-first, Open Source Semantic Toolkit for Managing and Querying Knowledge Graphs
https://github.com/geekjuruo/beer2
공식 코드Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
https://github.com/genetasefa/raild
공식 코드RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
https://github.com/gengchenmai/Attention_GraphQA
공식 코드Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs
https://github.com/geofila/Semantic-Counterfactuals
공식 코드Choose your Data Wisely: A Framework for Semantic Counterfactuals
https://github.com/giacoballoccu/explanation-quality-recsys
공식 코드https://github.com/gipplab/MathQA
공식 코드Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling
https://github.com/gipplab/cl-osa
공식 코드Detecting Cross-Language Plagiarism using Open Knowledge Graphs
https://github.com/gknl/smile
공식 코드SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction
https://github.com/glaciohound/lerp
공식 코드Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
https://github.com/google-research/smore
공식 코드SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
https://github.com/graphcore-research/kg-topology-toolbox
공식 코드The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models
https://github.com/graphdeeplearning/graphtransformer
공식 코드https://github.com/graphpku/open-world-kg
공식 코드Rethinking Knowledge Graph Evaluation Under the Open-World Assumption
https://github.com/gsp2014/NaLP
공식 코드Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
https://github.com/guanzhou-ke/knowledge-bridger
공식 코드Knowledge Bridger: Towards Training-free Missing Modality Completion
https://github.com/guojiapub/bique
공식 코드https://github.com/gurdaspuriya/walk-and-relate
공식 코드https://github.com/gychant/CSKMTermDefn
공식 코드https://github.com/h324yang/HMAN
공식 코드Aligning Cross-Lingual Entities with Multi-Aspect Information
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.