Julia M. Taylor

A natural language exchange model for enabling human, agent, robot and machine interaction

Models of communications in heterogeneous systems support exchange between agents of different types. A key component is making the heterogeneous agents appear indistinguishable to and from each other in terms of language, to normalize communication. A goal is to act as an open system, where the agents can come and exit as needed by the requirements of the overall goal of the system. The main goal of this research is the creation of a communicative model to support interaction, organization and collective intelligence features between a heterogeneous set of agents as machines, robots, software agents, and humans, all working in a cooperative organization. Communication appears as a natural language interface between all agents to enable clear, indistinguishable communication between all within the organization.

Ontological semantic technology for detecting insider threat and social engineering

This paper describes a computational system for detecting unintentional inferences in casual unsolicited and unrestricted verbal output of individuals, potentially responsible for leaked classified information to people with unauthorized access. Uses of the system for cases of insider threat and/or social engineering are discussed. Brief introductions to Ontological Semantic Technology and Natural Language Information Assurance and Security are included.

Understanding the unknown: Unattested input processing in natural language

This paper describes the process of deriving the meaning of an unknown word within the framework of meaning based natural language processing. It uses the clues supplied by the rest of the sentence, taking into account various degrees of possibilities of what the unknown word can mean, according to the previously acquired knowledge resources. The process of finding the meaning is incremental, and thus the derived meaning can evolve as more knowledge is gathered. The paper describes the fuzzy approach to the problem within this framework with regard to the semantic and syntactic acceptability of a sentence.

Fuzzy ontology for natural language

The paper outlines a framework for a full incorporation of fuzziness into a comprehensive system of natural language meaning processing with the help of ontological semantic technology. It goes far beyond the traditional examples of fuzziness for natural language modifiers, claiming that fuzziness is pervasive throughout natural language and cannot be avoided without a considerable penalty on accuracy.

The (not so) unbearable fuzziness of natural language: The ontological semantic way of computing with words

Extending the idea of computing with words in place of numbers to computing with words in a free, unstructured text, the paper presents the ontological semantics theory, methodology and technology for accessing, formally representing, and computing natural language to achieve a near-human understanding of it. It also demonstrates how ontological semantics handles various types of uncertainty, fuzziness, and vagueness that are built into natural language and are mostly happily ignored by the native speakers. The paper appears to be the first attempt ever to directly relate fuzzy sets/logic to the fullscale meaning-based approach to natural language and it computational processing.

An unintentional inference and ontological property defaults

A recent Facebook update informed a users friends that, on a night out at a bar, “a white dude was hitting on me all night”. It occurred to a couple of us independently that the user was not white or at least very likely not to be white, which was actually confirmed by those in the know. This paper is an attempt to explore and explain, the nature of this and similar inferences and to sketch out a way to compute them. A thorough search by a noted pragmaticist, in our ranks, has failed to produce any similar study, and it is borne out by the map and trends in the field. We have also realized that the inference can serve as a new and more rigorous explanation for a large class of jokes that none of us, humor researchers all (among other things), has ever seen analyzed that way. The largely formalism-free façade of the paper should not distract a reader from the technical nature of the argument.

Ontology-based view of natural language meaning: the case of humor detection

This paper deals with computational detection of humor. It assumes that computational humor is an useful task for any number of reasons and in many applications. Besides these applications, it also shows that recognition of humor is a perfect test platform for an advanced level of language understanding by a computer. It discusses the computational linguistic/semantic preconditions for computational humor and an ontological semantic approach to the task of humor detection, based on direct and comprehensive access to meaning rather than on trying to guess it with statistical-cum-syntactical keyword methods. The paper is informed by the experience of designing and implementing a humor detection model, whose decent success rate confirmed some of the assumptions while its flaws made other ideas prominent, including the necessity of full text comprehension. The bulk of the paper explains how the comprehensive meaning access technology makes it possible for unstructured natural language text to be automatically translated into the ontologically defined text meaning representations that can be used then to detect humor in them, if any, automatically. This part is informed by the experience, subsequent to humor detection, of designing, implementing, and testing an ontological semantic text analyzer that takes an English sentence as input and outputs its text meaning representation (TMR). Every procedure mentioned in the paper has either been implemented or proven to be implementable within the approach.

Computing with nouns and verbs

The paper makes a case for expanding the range of words that Computing With Words typically considers to, eventually, all the words in a natural language, thus accounting accurately for the inherent vagueness of natural language meaning and creating an overlap with computational semantics. The claim is illustrated with examples of a few English nouns and verbs rather than the usual adjectives and their close derivatives.

Design of Knowledge-Based Communication between Human and Robot Using Ontological Semantic Technology in Firefighting Domain

This paper discusses how to design robot-human communication using Ontological Semantic Technology (OST), which is to address meanings of phrases or sentences in natural languages, in a firefighting domain. The OST is a system in an ontology-based structure to deal with different natural languages. In this study, English and Korean were selected to be implemented for the OST. The problem set is designed with Natural English, direct translation from the natural English to Korean, natural Korean, and direct translation from the natural Korean to English, which can be compared to examine the similarity of meanings with a language-independent ontology in processing English and Korean.

Meaning- and ontology-based technologies for high-precision language an information-processing computational systems

The paper addresses the need for an ontology- and meaning-based approach for natural-language-understanding and information-processing computational systems. After a discussion of an oft-ignored form/content dichotomy that offers an explicit understanding of what meaning is and is not, a specific approach, the Ontological Semantic Technology, is introduced and several aspects of meaning representation are addressed in its terms, including how the 1977 Tenerife fatal aircrash could have been prevented with its help.