Joana Hois

A linguistic ontology of space for natural language processing

We present a detailed semantics for linguistic spatial expressions supportive of computational processing that draws substantially on the principles and tools of ontological engineering and formal ontology. We cover language concerned with space, actions in space and spatial relationships and develop an ontological organization that relates such expressions to general classes of fixed semantic import. The result is given as an extension of a linguistic ontology, the Generalized Upper Model, an organization which has been used for over a decade in natural language processing applications. We describe the general nature and features of this ontology and show how we have extended it for working particularly with space. Treaitng the semantics of natural language expressions concerning space in this way offers a substantial simplification of the general problem of relating natural spatial language to its contextualized interpretation. Example specifications based on natural language examples are presented, as well as an evaluation of the ontologys coverage, consistency, predictive power, and applicability.

Spatio-terminological inference for the design of ambient environments

We present an approach to assist the smart environment design process by means of automated validation of work-in-progress designs. The approach facilitates validation of not only the purely structural requirements, but also the functional requirements expected of a smart environment whilst keeping in mind the plethora of sensory and interactive devices embedded within such an environment. The approach, founded in spatio-terminological reasoning, is illustrated in the context of formal ontology modeling constructs and reasoners, industrial architecture data standards and state-of-the-art commercial design software.

Ontological modelling of form and function for architectural design

Form, function and the relationship between the two serve a crucial role in design. Within architectural design, key aspects of the anticipated function of buildings, or of spatial environments in general, are supposed to be supported by their structural form, i.e., their shape, layout, or connectivity. Whereas the philosophy of form and function is a well-researched topic, the practical relations and dependencies between form and function are only known implicitly by designers and architects. Specifically, the formal modelling of structural forms and resulting artefactual functions within design and design assistance systems remains elusive.In our work, we aim at making these definitions explicit by ontologically modelling respective domain entities, their properties and related constraints. We interpret “structural form” and “artefactual function” by specifying modular ontologies and their interplay for the architectural design domain. A key aspect in our modelling approach is the use of formal conceptual requirements and qualitative spatial calculi as a link between the structural form of a design and the differing functional capabilities that it affords or leads to. We demonstrate how our ontological modelling reflects types of architectural form and function, and how it facilitates the conceptual modelling of requirement constraints in architectural design.

Natural Language Meets Spatial Calculi

We address the problem of relating natural language descriptions of spatial situations with spatial logical calculi, focusing on projective terms (orientations). We provide a formalism based on the theory of

Dialog-based 3D-image recognition using a domain ontology

\mathcal{E}

Modelling functional requirements in spatial design

-connections that connects natural language and spatial calculi. Semantics of linguistic expressions are specified in a linguistically motivated ontology, the Generalized Upper Model. Spatial information is specified as qualitative spatial relationships, namely orientations from the double-cross calculus. This linguistic-spatial connection cannot be adequately formulated without certain contextual, domain-specific aspects. We therefore extend the framework of

Modularizing spatial ontologies for assisted living systems

\mathcal{E}

Ontologizing Metadata for Assistive Technologies - The OASIS Repository

-connections twofold: (1) external descriptions narrow down the class of intended models, and (2) context-dependencies inherent in natural language descriptions feed back into the representation finite descriptions of necessary context information.

Towards ontological blending

The combination of vision and speech, together with the resulting necessity for formal representations, builds a central component of an autonomous system. A robot that is supposed to navigate autonomously through space must be able to perceive its environment as automatically as possible. But each recognition system has its own inherent limits. Especially a robot whose task is to navigate through unknown terrain has to deal with unidentified or even unknown objects, thus compounding the recognition problem still further. The system described in this paper takes this into account by trying to identify objects based on their functionality where possible. To handle cases where recognition is insufficient, we examine here two further strategies: on the one hand, the linguistic reference and labeling of the unidentified objects and, on the other hand, ontological deduction. This approach then connects the probabilistic area of object recognition with the logical area of formal reasoning. In order to support formal reasoning, additional relational scene information has to be supplied by the recognition system. Moreover, for a sound ontological basis for these reasoning tasks, it is necessary to define a domain ontology that provides for the representation of real-world objects and their corresponding spatial relations in linguistic and physical respects. Physical spatial relations and objects are measured by the visual system, whereas linguistic spatial relations and objects are required for interactions with a user.

Modularity in ontologies

We demonstrate the manner in which high-level design requirements, e.g., as they correspond to the commonsensical conceptualisation of expert designers, may be formally specified within practical information systems, wherein heterogeneous perspectives and conceptual commitments are needed. Focussing on semantics, modularity and consistency, we argue that our formalisation serves as a synergistic interface that mediates between the two disconnected domains of human abstracted qualitative/conceptual knowledge and its quantitative/precision-oriented counterpart within systems for spatial design (assistance). Our demonstration utilises simple, yet real world examples.