Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
- URL: http://arxiv.org/abs/2010.03158v2
- Date: Thu, 8 Oct 2020 07:54:24 GMT
- Title: Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
- Authors: Xuelu Chen, Muhao Chen, Changjun Fan, Ankith Uppunda, Yizhou Sun,
Carlo Zaniolo
- Abstract summary: Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning.
We propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs.
Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion.
- Score: 43.453915033312114
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Predicting missing facts in a knowledge graph (KG) is a crucial task in
knowledge base construction and reasoning, and it has been the subject of much
research in recent works using KG embeddings. While existing KG embedding
approaches mainly learn and predict facts within a single KG, a more plausible
solution would benefit from the knowledge in multiple language-specific KGs,
considering that different KGs have their own strengths and limitations on data
quality and coverage. This is quite challenging, since the transfer of
knowledge among multiple independently maintained KGs is often hindered by the
insufficiency of alignment information and the inconsistency of described
facts. In this paper, we propose KEnS, a novel framework for embedding learning
and ensemble knowledge transfer across a number of language-specific KGs. KEnS
embeds all KGs in a shared embedding space, where the association of entities
is captured based on self-learning. Then, KEnS performs ensemble inference to
combine prediction results from embeddings of multiple language-specific KGs,
for which multiple ensemble techniques are investigated. Experiments on five
real-world language-specific KGs show that KEnS consistently improves
state-of-the-art methods on KG completion, via effectively identifying and
leveraging complementary knowledge.
Related papers
- Context Graph [8.02985792541121]
We present a context graph reasoning textbfCGR$3$ paradigm that leverages large language models (LLMs) to retrieve candidate entities and related contexts.
Our experimental results demonstrate that CGR$3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks.
arXiv Detail & Related papers (2024-06-17T02:59:19Z) - KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge [63.19837262782962]
Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph.
This study introduces KG-FIT, which builds a semantically coherent hierarchical structure of entity clusters.
Experiments on the benchmark datasets FB15K-237, YAGO3-10, and PrimeKG demonstrate the superiority of KG-FIT over state-of-the-art pre-trained language model-based methods.
arXiv Detail & Related papers (2024-05-26T03:04:26Z) - Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [87.67177556994525]
We propose a training-free method called Generate-on-Graph (GoG) to generate new factual triples while exploring Knowledge Graphs (KGs)
GoG performs reasoning through a Thinking-Searching-Generating framework, which treats LLM as both Agent and KG in IKGQA.
arXiv Detail & Related papers (2024-04-23T04:47:22Z) - FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph
Completion [21.4302940596294]
Knowledge graph completion (KGC) aims to predict missing facts in knowledge graphs (KGs)
Previous methods that rely on transferring raw data among KGs raise privacy concerns.
We propose a new federated learning framework that implicitly aggregates knowledge from multiple KGs without demanding raw data exchange and entity alignment.
arXiv Detail & Related papers (2023-12-17T08:09:27Z) - Collective Knowledge Graph Completion with Mutual Knowledge Distillation [11.922522192224145]
We study the problem of multi-KG completion, where we focus on maximizing the collective knowledge from different KGs.
We propose a novel method called CKGC-CKD that uses relation-aware graph convolutional network encoder models on both individual KGs and a large fused KG.
Experimental results on multilingual datasets have shown that our method outperforms all state-of-the-art models in the KGC task.
arXiv Detail & Related papers (2023-05-25T09:49:40Z) - A Survey On Few-shot Knowledge Graph Completion with Structural and
Commonsense Knowledge [3.4012007729454807]
Few-shot KG completion (FKGC) requires the strengths of graph representation learning and few-shot learning.
This paper introduces FKGC challenges, commonly used KGs, and CKGs.
We then systematically categorize and summarize existing works in terms of the type of KGs and the methods.
arXiv Detail & Related papers (2023-01-03T16:00:09Z) - Reasoning over Multi-view Knowledge Graphs [59.99051368907095]
ROMA is a novel framework for answering logical queries over multi-view KGs.
It scales up to KGs of large sizes (e.g., millions of facts) and fine-granular views.
It generalizes to query structures and KG views that are unobserved during training.
arXiv Detail & Related papers (2022-09-27T21:32:20Z) - 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) - FedE: Embedding Knowledge Graphs in Federated Setting [21.022513922373207]
Multi-Source KG is a common situation in real Knowledge Graph applications.
Because of the data privacy and sensitivity, a set of relevant knowledge graphs cannot complement each other's KGC by just collecting data from different knowledge graphs together.
We propose a Federated Knowledge Graph Embedding framework FedE, focusing on learning knowledge graph embeddings by aggregating locally-computed updates.
arXiv Detail & Related papers (2020-10-24T11:52:05Z) - On the Role of Conceptualization in Commonsense Knowledge Graph
Construction [59.39512925793171]
Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs.
We introduce to CKG construction methods conceptualization to view entities mentioned in text as instances of specific concepts or vice versa.
Our methods can effectively identify plausible triples and expand the KG by triples of both new nodes and edges of high diversity and novelty.
arXiv Detail & Related papers (2020-03-06T14:35:20Z)
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.