paper-with-me

홈 › Papers

Knowledge Graph Error Detection with Contrastive Confidence Adaption

2023-12-19 · Xiangyu Liu, Yang Liu, Wei Hu

Knowledge graphs (KGs) often contain various errors. Previous works on detecting errors in KGs mainly rely on triplet embedding from graph structure. We conduct an empirical study and find that these works struggle to discriminate noise from semantically-similar correct triplets. In this paper, we propose a KG error detection model CCA to integrate both textual and graph structural information from triplet reconstruction for better distinguishing semantics. We design interactive contrastive learning to capture the differences between textual and structural patterns. Furthermore, we construct realistic datasets with semantically-similar noise and adversarial noise. Experimental results demonstrate that CCA outperforms state-of-the-art baselines, especially in detecting semantically-similar noise and adversarial noise.

📄 PDF Abstract BibTeX arXiv:2312.12108

Code (1)

nju-websoft/cca 공식 구현 pytorch

Tasks

Contrastive LearningKnowledge GraphsTriplet

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Contrastive Knowledge Graph Error Detection

2022-11-18 · Qinggang Zhang, Junnan Dong, Keyu Duan, Xiao Huang 외

Knowledge Graph (KG) errors introduce non-negligible noise, severely affecting KG-related downstream tasks. Detecting errors in KGs is challenging since the patterns of errors are unknown and diverse, while ground-truth …

Contrastive Learning

SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement

2019-02-18 · Yu Zhao, Ji Liu

Knowledge graph (KG) refinement mainly aims at KG completion and correction (i.e., error detection). However, most conventional KG embedding models only focus on KG completion with an unreasonable assumption that all fac…

Translation

How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals

2026-04-24 · Dharshan Kumaran, Viorica Patraucean, Simon Osindero, Petar Veličković 외 arxiv

Large language models can detect their own errors and sometimes correct them without external feedback, but the underlying mechanisms remain unknown. We investigate this through the lens of second-order models of confide…

Contrastive Object Detection Using Knowledge Graph Embeddings

2021-12-21 · Christopher Lang, Alexander Braun, Abhinav Valada

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a backgrou…

Knowledge Graph EmbeddingsKnowledge GraphsObjectobject-detection+3

Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence

2017-05-09 · Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin

Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that sti…

Knowledge Graph CompletionKnowledge GraphsRepresentation LearningTriple Classification