Lattice-preserving $\mathcal{ALC}$ ontology embeddings
- URL: http://arxiv.org/abs/2305.07163v2
- Date: Wed, 8 May 2024 08:57:15 GMT
- Title: Lattice-preserving $\mathcal{ALC}$ ontology embeddings
- Authors: Fernando Zhapa-Camacho, Robert Hoehndorf,
- Abstract summary: We propose an order-preserving embedding method to generate embeddings on a graph out of We, the semantics of which are expressed in Logics Descriptions (DLs)
We show that our method outperforms state-the-art theory-of-of-the-art embedding methods in several knowledge base completion tasks.
- Score: 50.05281461410368
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generating vector representations (embeddings) of OWL ontologies is a growing task due to its applications in predicting missing facts and knowledge-enhanced learning in fields such as bioinformatics. The underlying semantics of OWL ontologies is expressed using Description Logics (DLs). Initial approaches to generate embeddings relied on constructing a graph out of ontologies, neglecting the semantics of the logic therein. Recent semantic-preserving embedding methods often target lightweight DL languages like $\mathcal{EL}^{++}$, ignoring more expressive information in ontologies. Although some approaches aim to embed more descriptive DLs like $\mathcal{ALC}$, those methods require the existence of individuals, while many real-world ontologies are devoid of them. We propose an ontology embedding method for the $\mathcal{ALC}$ DL language that considers the lattice structure of concept descriptions. We use connections between DL and Category Theory to materialize the lattice structure and embed it using an order-preserving embedding method. We show that our method outperforms state-of-the-art methods in several knowledge base completion tasks. We make our code and data available at https://github.com/bio-ontology-research-group/catE.
Related papers
- Enhancing Geometric Ontology Embeddings for $\mathcal{EL}^{++}$ with Negative Sampling and Deductive Closure Filtering [45.817946135388176]
Ontology embeddings map classes, relations, and individuals in into $mathbbn$, and within $bbRn$ similarity between entities can be computed.
We develop novel negative losses that account both for the deductive closure and different types of negatives.
arXiv Detail & Related papers (2024-05-08T07:50:21Z) - Dual Box Embeddings for the Description Logic EL++ [16.70961576041243]
Similar to Knowledge Graphs (KGs), Knowledge Graphs are often incomplete, and maintaining and constructing them has proved challenging.
Similar to KGs, a promising approach is to learn embeddings in a latent vector space, while additionally ensuring they adhere to the semantics of the underlying DL.
We propose a novel ontology embedding method named Box$2$EL for the DL EL++, which represents both concepts and roles as boxes.
arXiv Detail & Related papers (2023-01-26T14:13:37Z) - Integrating Language Guidance into Vision-based Deep Metric Learning [78.18860829585182]
We propose to learn metric spaces which encode semantic similarities as embedding space.
These spaces should be transferable to classes beyond those seen during training.
This causes learned embedding spaces to encode incomplete semantic context and misrepresent the semantic relation between classes.
arXiv Detail & Related papers (2022-03-16T11:06:50Z) - Taxonomy Enrichment with Text and Graph Vector Representations [61.814256012166794]
We address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy.
We present a new method that allows achieving high results on this task with little effort.
We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.
arXiv Detail & Related papers (2022-01-21T09:01:12Z) - Why Settle for Just One? Extending EL++ Ontology Embeddings with
Many-to-Many Relationships [2.599882743586164]
Knowledge Graph embeddings provide a low-dimensional representation of entities and relations of a Knowledge Graph.
Recent efforts in this direction involve learning embeddings for a Description (logical Logic for a description) named EL++.
We provide a simple and effective solution that allows such methods to consider many-to-many relationships while learning embedding representations.
arXiv Detail & Related papers (2021-10-20T13:23:18Z) - Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling [65.51280121472146]
We exploit what we intrinsically know about ontology labels to build efficient semantic parsing models.
Our model is highly efficient using a low-resource benchmark derived from TOPv2.
arXiv Detail & Related papers (2021-04-15T04:01:02Z) - Learning Description Logic Ontologies. Five Approaches. Where Do They
Stand? [14.650545418986058]
We highlight machine learning and data mining approaches that have been proposed for the creation of description logic (DL)
These are based on association rule mining, formal concept analysis, inductive logic programming, computational learning theory, and neural networks.
arXiv Detail & Related papers (2021-04-02T18:36:45Z) - Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50.
Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
arXiv Detail & Related papers (2020-09-12T17:36:53Z) - Asking without Telling: Exploring Latent Ontologies in Contextual
Representations [12.69022456384102]
We show that pretrained contextual encoders learn to encode meaningful notions of linguistic structure without explicit supervision.
Our results provide new evidence of emergent structure in pretrained encoders, including departures from existing annotations.
arXiv Detail & Related papers (2020-04-29T23:20:40Z)
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.