EL Embeddings: Geometric Construction of Models for the Description Logic EL++

Kulmanov, Maxat; Liu-Wei, Wang; Yuan, Yan; Hoehndorf, Robert

doi:10.24963/ijcai.2019/845

Cited by 69 publications

(89 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 concludes about the key characteristics of sim , compared to the others in logic-based methods. Symbolic ⇒ Neuro Virtualization [10] Symbolic ⇒ Neuro Virtualization [19] Symbolic ⇒ Neuro Virtualization [11] Symbolic ⇒ Neuro Virtualization [12] Symbolic ⇒ Neuro Virtualization [29] Symbolic ⇒ Neuro Virtualization [30] Symbolic ⇒ Neuro Virtualization [31] Symbolic ⇒ Neuro Virtualization sim Neuro ⇒ Symbolic Formal semantics (symbolic part) and virtualization (neuro part) Description tree…”

Section: A On the Viewpoint Of Ontology Similaritymentioning

confidence: 99%

“…Finally, embeddings can be trained subject to the interpretation function I and preserve semantics defined for each logical constructs of DLs. For intance, Hoehndorf et al [31] specifically formalized loss functions corresponding to the constructs provided by the logic EL ++ , i.e., the constructors intersection, existential quantifiers, and bottom.…”

Section: B On the Viewpoint Of Neuro-symbolismmentioning

confidence: 99%

See 1 more Smart Citation

On Approximation of Concept Similarity Measure in Description Logic ELH With Pre-Trained Word Embedding

Racharak

2021

IEEE Access

View full text Add to dashboard Cite

Data-driven and knowledge-driven methods are two mainstream techniques in the pursuit of developing artificial intelligence systems. While data-driven methods seek to develop a decision model from observations in the real world, they are difficult to provide an explanation for the results in human terms. On the other hand, knowledge-driven methods that employ symbolic reasoning based on formal semantics of a knowledge-base are thus more interpretable and explainable, while lacking an ability to deal with incomplete modeling of the structured knowledge-bases. This work aims to tackle these issues on ontology similarity by proposing a general framework that combines the strengths of both approaches for measuring semantic similarity of concepts in a description logic (DL) ontology. More specifically, a neuro-symbolic integrated framework is defined to exploit the pre-trained word embeddings with semantic definitions in an ontology to yield an explainable degree of concept similarity. To demonstrate its applicability, we develop a concrete similarity measure sim conforming to the proposed framework and also introduce an efficient algorithm that can extract an explanation for why such a degree is indicated. The correctness is shown by analyzing theoretical properties that it guarantees to preserve and also by performing an empirical evaluation with a medical ontology SNOMED CT and a medical pre-trained embedding BioWordVec. The results show that our proposed method remains both interpretability and explainability while achieving comparable performance, relative to the state-of-the-art approaches in the data and knowledge-driven methods.

show abstract

Section: A On the Viewpoint Of Ontology Similaritymentioning

confidence: 99%

Section: B On the Viewpoint Of Neuro-symbolismmentioning

confidence: 99%

On Approximation of Concept Similarity Measure in Description Logic ELH With Pre-Trained Word Embedding

Racharak

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…An early example is (d'Amato et al 2009), which proposed to use a similarity metric between individuals to find plausible answers to queries. More recently, Bouraoui and Schockaert (2018) proposed a method for finding plausible missing ABox assertions, by representing each concept as a Gaussian distribution in a vector space, while Kulmanov et al (2019) proposed a method to learn a vector space embedding of EL ontologies for this purpose. The problem of completing TBoxes using vector space representations was considered in (Bouraoui and Schockaert 2019).…”

Section: Related Workmentioning

confidence: 99%

Plausible Reasoning about EL-Ontologies using Concept Interpolation

Ibáñez-García

Gutiérrez-Basulto

Schockaert

2020

Proceedings of the Seventeenth International Conference on Principles of Knowledge Representation and Reasoning

View full text Add to dashboard Cite

Description logics (DLs) are standard knowledge representation languages for modelling ontologies, i.e. knowledge about concepts and the relations between them. Unfortunately, DL ontologies are difficult to learn from data and time-consuming to encode manually. As a result, ontologies for broad domains are almost inevitably incomplete. In recent years, several data-driven approaches have been proposed for automatically extending such ontologies. One family of methods rely on characterizations of concepts that are derived from text descriptions. While such characterizations do not capture ontological knowledge directly, they encode information about the similarity between different concepts that can be exploited for filling in the gaps in existing ontologies. To this end, several inductive inference mechanisms have already been proposed, but these have been defined and used in a heuristic fashion. In this paper, we instead propose an inductive inference mechanism which is based on a clear model-theoretic semantics, and can thus be tightly integrated with standard deductive reasoning. We particularly focus on interpolation, a powerful commonsense reasoning mechanism which is closely related to cognitive models of category-based induction. Apart from the formalization of the underlying semantics, as our main technical contribution we provide computational complexity bounds for reasoning in EL with this interpolation mechanism.

show abstract

“…Embedding the classes, relations, and instances in ontologies can provide useful features for predictive models that rely on background knowledge, and these embeddings can incorporate ontology axioms as well as natural language annotations such as labels and definitions (Kulmanov et al, 2019;Liu-Wei et al, 2019;Althubaiti et al, 2019;Smaili et al, 2018a). However, using the natural language information in ontologies can also add noise, in particular when labels or descriptions use complex terms, such as chemical formulas, which are not easy to recognize in natural language text (Smaili et al, 2019).…”

Section: Ontology-based Normalization Of Natural Languagementioning

confidence: 99%

“…We apply these normalization methods so that we can utilize literature and ontologies jointly in machine learning models. Ontology-based machine learning methods mainly use the formal axioms and entity-class annotations without considering natural language information (Smaili et al, 2018a;Kulmanov et al, 2019;Holter et al, 2019). At the same time, there are a number of methods which apply learning on literature directly to perform biomedical analysis and prediction tasks (Kim et al, 2019;Naeem et al, 2010;Wong and Shatkay, 2013).…”

Section: Introductionmentioning

confidence: 99%

Self-normalizing learning on biomedical ontologies using a deep Siamese neural network

Smaili

Gao

Hoehndorf

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation:Ontologies are widely used in biomedicine for the annotation and standardization of data. One of the main roles of ontologies is to provide structured background knowledge within a domain as well as a set of labels, synonyms, and definitions for the classes within a domain. The two types of information provided by ontologies have been extensively exploited in natural language processing and machine learning applications. However, they are commonly used separately, and thus it is unknown if joining the two sources of information can further benefit data analysis tasks. Results: We developed a novel method that applies named entity recognition and normalization methods on texts to connect the structured information in biomedical ontologies with the information contained in natural language. We apply this normalization both to literature and to the natural language information contained within ontologies themselves. The normalized ontologies and text are then used to generate embeddings, and relations between entities are predicted using a deep Siamese neural network model that takes these embeddings as input. We demonstrate that our novel embedding and prediction method using self-normalized biomedical ontologies significantly outperforms the state-of-the-art methods in embedding ontologies on two benchmark tasks: prediction of interactions between proteins and prediction of gene-disease associations. Our method also allows us to apply ontology-based annotations and axioms to the prediction of toxicological effects of chemicals where our method shows superior performance. Our method is generic and can be applied in scenarios where ontologies consisting of both structured information and natural language labels or synonyms are used.

show abstract

EL Embeddings: Geometric Construction of Models for the Description Logic EL++

Cited by 69 publications

References 0 publications

On Approximation of Concept Similarity Measure in Description Logic ELH With Pre-Trained Word Embedding

On Approximation of Concept Similarity Measure in Description Logic ELH With Pre-Trained Word Embedding

Plausible Reasoning about EL-Ontologies using Concept Interpolation

Self-normalizing learning on biomedical ontologies using a deep Siamese neural network

Contact Info

Product

Resources

About