Pith. sign in

REVIEW 35 cited by

KG-BERT: BERT for Knowledge Graph Completion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1909.03193 v2 pith:GGC4SKMJ submitted 2019-09-07 cs.CL cs.AI

Liang Yao , Chengsheng Mao , Yuan Luo This is my paper · ORCID
classification cs.CLcs.AI
keywords knowledgegraphgraphskg-berttriplecompletionlanguagemethod
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness. In this work, we propose to use pre-trained language models for knowledge graph completion. We treat triples in knowledge graphs as textual sequences and propose a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples. Our method takes entity and relation descriptions of a triple as input and computes scoring function of the triple with the KG-BERT language model. Experimental results on multiple benchmark knowledge graphs show that our method can achieve state-of-the-art performance in triple classification, link prediction and relation prediction tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 35 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 381 citations worldwide. Full citation record

  1. Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning

    math.ST 2026-07 conditional novelty 6.0 of 10

    A four-term oracle inequality decomposes knowledge-graph prediction risk into approximation, estimation, optimization, and multi-view pretraining error, with a subspace-recovery guarantee for kernel PCA pretraining.

  2. RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    RADD decouples retrieval and reranking in multi-modal KGC via a relation-aware KGE retriever and conditional discrete denoiser, reporting state-of-the-art results on three benchmarks.

  3. Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge

    cs.AI 2026-01 reject novelty 6.0 of 10

    ExeFuse uses learned 'logic' transformations and density checks to fuse general-graph facts into domain knowledge graphs, but the benchmark labels and baseline comparisons are too underspecified to support the claimed gains.

  4. Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs

    cs.CL 2025-09 conditional novelty 6.0 of 10

    A self-supervised pipeline that pairs fine-tuned SBERT with a skill knowledge graph reduces RMSE for highly related job title pairs to 0.11, about 25% to 39% below strong baselines.

  5. Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

    cs.CL 2025-09 reject novelty 6.0 of 10

    SAT uses hierarchical contrastive alignment and a unified graph instruction to tune a lightweight adapter for knowledge graph completion, reporting large link prediction gains.

  6. Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning

    cs.MM 2025-07 conditional novelty 6.0 of 10

    A unimodal student model, taught by reinforcement-selected combinations of multimodal teachers via neighbor-decoupled knowledge distillation, sets new state-of-the-art results on five multimodal knowledge graph reason...

  7. BioGraphFusion: Graph Knowledge Embedding for Biological Completion and Reasoning

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A hybrid semantic-structural graph model with CP decomposition, LSTM-based relation refinement, query-guided subgraph propagation, and a blended scoring function reports state-of-the-art accuracy on three biomedical k...

  8. Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A masked diffusion imputer plus dual distillation (MMFeD3-HidE) improves link prediction on a new federated multimodal knowledge graph benchmark with 50% missing visual/textual modalities.

  9. Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A survey of n-ary knowledge representation learning methods proposes a two-dimensional taxonomy based on modeling technique and entity role/position awareness.

  10. HERGC: Heterogeneous Experts Representation and Generative Completion for Multimodal Knowledge Graphs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    HERGC combines a multimodal expert-based retriever with a fine-tuned LLM re-ranker to achieve state-of-the-art multimodal knowledge graph completion on MKG-W, MKG-Y, and DB15K.

  11. K-ON: Stacking Knowledge On the Head Layer of Large Language Model

    cs.CL 2025-02 conditional novelty 6.0 of 10

    K-ON stacks K prediction heads onto an LLM to generate entity tokens in one step and uses entity-level contrastive learning, achieving new state-of-the-art results on two knowledge graph completion benchmarks.

  12. Graph-based Document Structure Analysis

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A new document understanding task and dataset (GraphDoc) that labels how text blocks, tables, and figures relate in space and in logic, with a baseline model reaching 57.6% graph mAP.

  13. Enhancing Transformers for Generalizable First-Order Logical Entailment

    cs.CL 2025-01 conditional novelty 6.0 of 10

    Transformers with relative positional encoding beat KGQA baselines, and adding logic-aware attention (TEGA) improves out-of-distribution performance on a new 55-type benchmark.

  14. Deep Sparse Latent Feature Models for Knowledge Graph Completion

    cs.CL 2024-11 conditional novelty 6.0 of 10

    DSLFM-KGC couples sparse latent community models with BERT text features and contrastive learning, improving state-of-the-art scores on Wikidata5M-Ind, WN18RR, and UMLS.

  15. Neurosymbolic Graph Enrichment for Grounded World Models

    cs.AI 2024-11 conditional novelty 6.0 of 10

    A neurosymbolic pipeline converts images into enriched knowledge graphs by combining LLM descriptions, AMR parsing, and LLM-generated implicit knowledge heuristics.

  16. Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning

    cs.CL 2026-07 conditional novelty 5.0 of 10

    A T5-based sentence splitter trained on verbalized knowledge-graph triples extracts prefix–tail pairs from raw text, and the resulting structure-aware supervision raises few-shot CommonsenseQA and ATOMIC completion scores.

  17. Automated Hierarchical Graph Construction for Multi-source Electronic Health Records

    stat.ML 2025-09 conditional novelty 5.0 of 10

    MASH aligns medical codes across institutions using optimal transport and builds hierarchical graphs, including the first automated hierarchies for VA local laboratory codes.

  18. mRAKL: Multilingual Retrieval-Augmented Knowledge Graph Construction for Low-Resourced Languages

    cs.CL 2025-07 conditional novelty 5.0 of 10

    mRAKL reformulates multilingual knowledge graph completion as question answering and shows that retrieving context from Wikipedia improves tail-entity prediction for Tigrinya and Amharic, with gains up to 8.79 points ...

  19. Language Models as Ontology Encoders

    cs.AI 2025-07 conditional novelty 5.0 of 10

    OnT combines pretrained language models with hyperbolic embeddings and role rotations to encode EL ontologies, and reports better axiom prediction and inference than existing methods.

  20. Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion

    cs.CL 2025-06 reject novelty 5.0 of 10

    A relation-prediction model that combines top-K edge message passing with a conditional flow matching auxiliary loss, reporting near-perfect relation prediction and a 25% relative MRR gain in entity prediction.

  21. Knowledge Graph Embeddings with Representing Relations as Annular Sectors

    cs.LG 2025-06 conditional novelty 5.0 of 10

    SectorE embeds relations as annular sectors in polar coordinates and entities as points, achieving competitive link prediction on FB15k-237, WN18RR, and YAGO3-10.

  22. Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph

    cs.CL 2024-11 reject novelty 5.0 of 10

    WTS couples retrieval-augmented generation with an LLM-built, evolving domain knowledge graph and reports SOTA gains, but its main experiments use test-set gold answers to construct the graph.

  23. Knowledge Bases in Support of Large Language Models for Processing Web News

    cs.CL 2024-11 conditional novelty 5.0 of 10

    BERTGraph, which adds rule-extracted relational graphs to BERT via a graph convolutional network, improves news classification accuracy over fine-tuned BERT on N24News and Snopes datasets.

  24. Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

    cs.AI 2024-11 conditional novelty 5.0 of 10

    KGR3 combines retrieval of entity contexts, LLM reasoning, and supervised re-ranking to improve knowledge graph completion, reporting state-of-the-art Hits@1 on FB15k237 and WN18RR.

  25. KLIPA: A Knowledge Graph and LLM-Driven QA Framework for IP Analysis

    cs.IR 2025-09 conditional novelty 4.0 of 10

    KLIPA integrates a Neo4j knowledge graph, RAG, and a ReAct agent for patent QA, and shows VQA-based graph construction beats OCR+LLM on extraction metrics.

  26. SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structure-injected frozen-LLM framework with contrastive training achieves small gains on WN18RR and FB15k-237 link prediction.

  27. Higher-Order Graph Databases

    cs.DB 2025-06 conditional novelty 4.0 of 10

    Encoding higher-order structures as heterogeneous property graphs lets standard graph databases support hyperedges, node-tuples, and subgraphs; a Neo4j-based prototype, ACID discussion, complexity analysis, and a GNN ...

  28. KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A bidirectional decoder with a graph-aware attention mask, knowledge-masked prediction, and contrastive sub-graph alignment achieves reported state-of-the-art link prediction on Wikidata5M and competitive results on WN18RR.

  29. GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs

    cs.AI 2025-05 conditional novelty 4.0 of 10

    GenIC uses a Mistral-based classifier and a T5-based generator to complete knowledge graph facts from a head entity, outperforming simple baselines on FB15k-237, WN18RR, and CoDEx, with evaluation caveats.

  30. Rethinking Regularization Methods for Knowledge Graph Completion

    cs.LG 2025-05 reject novelty 4.0 of 10

    A selective sparsity regularizer, SPR, nudges link prediction metrics up on standard benchmarks, but the evidence is single-run and the theoretical justification is mathematically flawed.

  31. Towards Structure-aware Model for Multi-modal Knowledge Graph Completion

    cs.MM 2025-05 conditional novelty 4.0 of 10

    TSAM combines token-level fusion of visual and textual data with structure-anchored contrastive learning, outperforming prior multi-modal KGC models on DB15K, MKG-W, and MKG-Y.

  32. A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects

    cs.AI 2025-04 conditional novelty 4.0 of 10

    A task-oriented survey of knowledge graph reasoning, covering six task categories, benchmark datasets, downstream applications, and future challenges.

  33. QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding

    cs.LG 2025-04 reject novelty 4.0 of 10

    QuatE-D replaces the inner-product scoring of QuatE with Euclidean distance after a quaternion Hamilton-product rotation, and reports improved Mean Rank on WN18, FB15k, WN18RR, and FB15k-237.

  34. A Contextualized BERT model for Knowledge Graph Completion

    cs.CL 2024-12 reject novelty 4.0 of 10

    CAB-KGC, a BERT classifier using head and relation context, reports Hit@1 of 0.322 on FB15k-237 and 0.637 on WN18RR, but the claimed SOTA gains do not match the paper's own comparison table.

  35. A survey on cutting-edge relation extraction techniques based on language models

    cs.CL 2024-11 conditional novelty 3.0 of 10

    A survey of 2020-2023 ACL-family papers on relation extraction finds BERT-based models dominate, while large language models like T5 show promise mainly in few-shot settings.

Pith tools