Knowledge representation and reasoning

About: Knowledge representation and reasoning is a research topic. Over the lifetime, 20078 publications have been published within this topic receiving 446310 citations. The topic is also known as: KR & KR².

Image-embodied Knowledge Representation Learning

Abstract: Entity images could provide significant visual information for knowledge representation learning. Most conventional methods learn knowledge representations merely from structured triples, ignoring rich visual information extracted from entity images. In this paper, we propose a novel Image-embodied Knowledge Representation Learning model (IKRL), where knowledge representations are learned with both triple facts and images. More specifically, we first construct representations for all images of an entity with a neural image encoder. These image representations are then integrated into an aggregated image-based representation via an attention-based method. We evaluate our IKRL models on knowledge graph completion and triple classification. Experimental results demonstrate that our models outperform all baselines on both tasks, which indicates the significance of visual information for knowledge representations and the capability of our models in learning knowledge representations with images.

DOGMA-MESS: a meaning evolution support system for interorganizational ontology engineering

Abstract: In this paper, we explore the process of interorganizational ontology engineering. Scalable ontology engineering is hard to do in interorganizational settings where there are many pre-existing organizational ontologies and rapidly changing collaborative requirements. A complex socio-technical process of ontology alignment and meaning negotiation is therefore required. In particular, we are interested in how to increase the efficiency and relevance of this process using context dependencies between ontological elements. We describe the DOGMA-MESS methodology and system for scalable, community-grounded ontology engineering. We illustrate this methodology with examples taken from a case of interorganizational competency ontology evolution in the vocational training domain.

BOnSAI: a smart building ontology for ambient intelligence

Abstract: This work introduces an ontology for incorporating Ambient Intelligence in Smart Buildings. The ontology extends and benefits from existing ontologies in the field, but also adds classes needed to sufficiently model every aspect of a service-oriented smart building system. Namely, it includes concepts modeling all functionality (i.e. services, operations, inputs, outputs, logic, parameters and environmental conditions), QoS (resources, QoS parameters), hardware (smart devices, sensors and actuators, appliances, servers) users and context (user profiles, moods, location, rooms etc.). The ontology is instantiated and put to use at the Smart Building setting of the International Hellenic University, enabling knowledge representation in machine-interpretable form and hence is expected to enhance service-based intelligent applications.

Using OWL to model biological knowledge

Abstract: Much has been written of the facilities for ontology building and reasoning offered for ontologies expressed in the Web Ontology Language (OWL). Less has been written about how the modelling requirements of different areas of interest are met by OWL-DL's underlying model of the world. In this paper we use the disciplines of biology and bioinformatics to reveal the requirements of a community that both needs and uses ontologies. We use a case study of building an ontology of protein phosphatases to show how OWL-DL's model can capture a large proportion of the community's needs. We demonstrate how Ontology Design Patterns (ODPs) can extend inherent limitations of this model. We give examples of relationships between more than two instances; lists and exceptions, and conclude by illustrating what OWL-DL and its underlying description logic either cannot handle in theory or because of lack of implementation. Finally, we present a research agenda that, if fulfilled, would help ensure OWL's wider take up in the life science community.

TransA: An Adaptive Approach for Knowledge Graph Embedding.

Abstract: Knowledge representation is a major topic in AI, and many studies attempt to represent entities and relations of knowledge base in a continuous vector space. Among these attempts, translation-based methods build entity and relation vectors by minimizing the translation loss from a head entity to a tail one. In spite of the success of these methods, translation-based methods also suffer from the oversimplified loss metric, and are not competitive enough to model various and complex entities/relations in knowledge bases. To address this issue, we propose \textbf{TransA}, an adaptive metric approach for embedding, utilizing the metric learning ideas to provide a more flexible embedding method. Experiments are conducted on the benchmark datasets and our proposed method makes significant and consistent improvements over the state-of-the-art baselines.