Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data

• URL: http://arxiv.org/abs/2201.08580v1
• Date: Fri, 21 Jan 2022 07:59:16 GMT
• Title: Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data
• Authors: Jiacheng Huang and Yao Zhao and Wei Hu and Zhen Ning and Qijin Chen and Xiaoxia Qiu and Chengfu Huo and Weijun Ren
• Abstract summary: We propose a new trustworthy method that exploits facts for a knowledge graph based on multi-sourced noisy data and existing facts in the KG. Specifically, we introduce a graph neural network with a holistic scoring function to judge the plausibility of facts with various value types. We present a truth inference model that incorporates data source qualities into the fact scoring function, and design a semi-supervised learning way to infer the truths from heterogeneous values.
• Score: 35.938323660176145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graphs (KGs) have become a valuable asset for many AI applications. Although some KGs contain plenty of facts, they are widely acknowledged as incomplete. To address this issue, many KG completion methods are proposed. Among them, open KG completion methods leverage the Web to find missing facts. However, noisy data collected from diverse sources may damage the completion accuracy. In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG. Specifically, we introduce a graph neural network with a holistic scoring function to judge the plausibility of facts with various value types. We design value alignment networks to resolve the heterogeneity between values and map them to entities even outside the KG. Furthermore, we present a truth inference model that incorporates data source qualities into the fact scoring function, and design a semi-supervised learning way to infer the truths from heterogeneous values. We conduct extensive experiments to compare our method with the state-of-the-arts. The results show that our method achieves superior accuracy not only in completing missing facts but also in discovering new facts.

Related papers

• Deep Outdated Fact Detection in Knowledge Graphs [13.711099395945988]
  This paper presents DEAN, a novel deep learning-based framework designed to identify outdated facts within Knowledge Graphs (KGs) DEAN distinguishes itself by capturing implicit structural information among facts through comprehensive modeling of both entities and relations. Experimental results demonstrate the effectiveness and superiority of DEAN over state-of-the-art baseline methods.
  arXiv  Detail & Related papers  (2024-02-06T05:58:15Z)
• Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning [71.8876256714229]
  We propose an entity-based contrastive learning framework for improving the robustness of knowledge-grounded dialogue systems. Our method achieves new state-of-the-art performance in terms of automatic evaluation scores.
  arXiv  Detail & Related papers  (2024-01-09T05:16:52Z)
• FactKG: Fact Verification via Reasoning on Knowledge Graphs [12.5437408722802]
  We introduce a new dataset, FactKG: Fact Verification via Reasoning on Knowledge Graphs. It consists of 108k natural language claims with five types of reasoning: One-hop, Conjunction, Existence, Multi-hop, and Negation. We develop a baseline approach and analyze FactKG over these reasoning types.
  arXiv  Detail & Related papers  (2023-05-11T06:08:49Z)
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion [69.55700751102376]
  Few-shot knowledge graph completion (FKGC) aims to predict missing facts for unseen relations with few-shot associated facts. Existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems. In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC)
  arXiv  Detail & Related papers  (2023-04-17T11:42:28Z)
• Contrastive Knowledge Graph Error Detection [11.637359888052014]
  We propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED) CAGED introduces contrastive learning into KG learning and provides a novel way of modeling KG. It outperforms state-of-the-art methods in KG error detection.
  arXiv  Detail & Related papers  (2022-11-18T05:01:19Z)
• Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network [111.67744771462873]
  This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs) It combines high-order reasoning into a graph convolutional network, namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
  arXiv  Detail & Related papers  (2022-07-14T10:16:56Z)
• BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models [65.51390418485207]
  We propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition, the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge. We deploy the approach to harvest KGs of over 400 new relations from different LMs.
  arXiv  Detail & Related papers  (2022-06-28T19:46:29Z)
• Typing Errors in Factual Knowledge Graphs: Severity and Possible Ways Out [11.534085606272242]
  We propose an active typing error detection algorithm that maximizes the utilization of both gold and noisy labels. The outcomes of this study provide guidelines for researchers to use noisy factual KGs.
  arXiv  Detail & Related papers  (2021-02-03T21:47:37Z)
• Efficient Knowledge Graph Validation via Cross-Graph Representation Learning [40.570585195713704]
  noisy facts are unavoidably introduced into Knowledge Graphs that could be caused by automatic extraction. We propose a cross-graph representation learning framework, i.e., CrossVal, which can leverage an external KG to validate the facts in the target KG efficiently.
  arXiv  Detail & Related papers  (2020-08-16T20:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.