Learning Rules from KGs Guided by Language Models
- URL: http://arxiv.org/abs/2409.07869v1
- Date: Thu, 12 Sep 2024 09:27:36 GMT
- Title: Learning Rules from KGs Guided by Language Models
- Authors: Zihang Peng, Daria Stepanova, Vinh Thinh Ho, Heike Adel, Alessandra Russo, Simon Ott,
- Abstract summary: Rule learning methods can be applied to predict potentially missing facts.
Ranking of rules is especially challenging over highly incomplete or biased KGs.
With the recent rise of Language Models (LMs) several works have claimed that LMs can be used as alternative means for KG completion.
- Score: 48.858741745144044
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Advances in information extraction have enabled the automatic construction of large knowledge graphs (e.g., Yago, Wikidata or Google KG), which are widely used in many applications like semantic search or data analytics. However, due to their semi-automatic construction, KGs are often incomplete. Rule learning methods, concerned with the extraction of frequent patterns from KGs and casting them into rules, can be applied to predict potentially missing facts. A crucial step in this process is rule ranking. Ranking of rules is especially challenging over highly incomplete or biased KGs (e.g., KGs predominantly storing facts about famous people), as in this case biased rules might fit the data best and be ranked at the top based on standard statistical metrics like rule confidence. To address this issue, prior works proposed to rank rules not only relying on the original KG but also facts predicted by a KG embedding model. At the same time, with the recent rise of Language Models (LMs), several works have claimed that LMs can be used as alternative means for KG completion. In this work, our goal is to verify to which extent the exploitation of LMs is helpful for improving the quality of rule learning systems.
Related papers
- KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models [55.39134076436266]
KG-CF is a framework tailored for ranking-based knowledge graph completion tasks.
KG-CF leverages LLMs' reasoning abilities to filter out irrelevant contexts, achieving superior results on real-world datasets.
arXiv Detail & Related papers (2025-01-06T01:52:15Z) - Anomaly Detection and Classification in Knowledge Graphs [1.2599533416395767]
We propose SEKA (SEeking Knowledge graph Anomalies), an unsupervised approach for the detection of abnormal triples and entities in Knowledge Graphs.
We also present TAXO, a taxonomy of possible anomaly types that can occur in a KG.
We evaluate both approaches using the four real-world KGs YAGO-1, KBpedia, Wikidata, and DSKG.
arXiv Detail & Related papers (2024-12-06T05:03:10Z) - 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) - ChatRule: Mining Logical Rules with Large Language Models for Knowledge
Graph Reasoning [107.61997887260056]
We propose a novel framework, ChatRule, unleashing the power of large language models for mining logical rules over knowledge graphs.
Specifically, the framework is initiated with an LLM-based rule generator, leveraging both the semantic and structural information of KGs.
To refine the generated rules, a rule ranking module estimates the rule quality by incorporating facts from existing KGs.
arXiv Detail & Related papers (2023-09-04T11:38:02Z) - KGxBoard: Explainable and Interactive Leaderboard for Evaluation of
Knowledge Graph Completion Models [76.01814380927507]
KGxBoard is an interactive framework for performing fine-grained evaluation on meaningful subsets of the data.
In our experiments, we highlight the findings with the use of KGxBoard, which would have been impossible to detect with standard averaged single-score metrics.
arXiv Detail & Related papers (2022-08-23T15:11:45Z) - MEKER: Memory Efficient Knowledge Embedding Representation for Link
Prediction and Question Answering [65.62309538202771]
Knowledge Graphs (KGs) are symbolically structured storages of facts.
KG embedding contains concise data used in NLP tasks requiring implicit information about the real world.
We propose a memory-efficient KG embedding model, which yields SOTA-comparable performance on link prediction tasks and KG-based Question Answering.
arXiv Detail & Related papers (2022-04-22T10:47:03Z) - EngineKGI: Closed-Loop Knowledge Graph Inference [37.15381932994768]
EngineKGI is a novel closed-loop KG inference framework.
It combines KGE and rule learning to complement each other in a closed-loop pattern.
Our model outperforms other baselines on link prediction tasks.
arXiv Detail & Related papers (2021-12-02T08:02:59Z) - What is Normal, What is Strange, and What is Missing in a Knowledge
Graph: Unified Characterization via Inductive Summarization [34.3446695203147]
We introduce a unified solution to KG characterization by formulating the problem as unsupervised KG summarization.
KGist learns a summary of inductive rules that best compress the KG according to the Minimum Description Length principle.
We show that KGist outperforms task-specific, supervised and unsupervised baselines in error detection and incompleteness identification.
arXiv Detail & Related papers (2020-03-23T17:38:31Z)
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.