Stephen Beale

Semantically Rich Human-Aided Machine Annotation

This paper describes a semantically rich, human-aided machine annotation system created within the Ontological Semantics (OntoSem) environment using the DEKADE toolset. In contrast to mainstream annotation efforts, this method of annotation provides more information at a lower cost and, for the most part, shifts the maintenance of consistency to the system itself. In addition, each tagging effort not only produces knowledge resources for that corpus, but also leads to improvements in the knowledge environment that will better support subsequent tagging efforts.

Knowledge-Based Modeling and Simulation of Diseases with Highly Differentiated Clinical Manifestations

This paper presents the cognitive model of gastroesophageal reflux disease (GERD) developed for the Maryland Virtual Patient simulation and mentoring environment. GERD represents a class of diseases that have a large number of clinical manifestations. Our model at once manages that complexity while offering robust automatic function in response to open-ended user actions. This ontologically grounded model is largely based on script-oriented representations of causal chains reflecting the actual physiological processes in virtual patients. A detailed description of the GERD model is presented along with a high-level description of the environment for which it was developed.

An NLP Lexicon as a Largely Language-Independent Resource

This paper describes salient aspects of the OntoSem lexicon of English, a lexicon whose semantic descriptions can either be grounded in a language-independent ontology, rely on extra-ontological expressive means, or exploit a combination of the two. The variety of descriptive means, as well as the conceptual complexity of semantic description to begin with, necessitates that OntoSem lexicons be compiled primarily manually. However, once a semantic description is created for a lexeme in one language, it can be reused in others, often with little or no modification. Said differently, the challenge in building a semantic lexicon is describing semantics; once the semantics are described, it is relatively straightforward to connect given meanings to the appropriate head words in other languages. In this paper we provide a brief overview of the OntoSem lexicon and processing environment, orient our approach to lexical semantics among others in the field, and describe in more detail what we mean by the largely language-independent lexicon. Finally, we suggest reasons why our resources might be of interest to the larger community.

Evaluating the performance of the OntoSem semantic analyzer

This paper describes an innovative evaluation regimen developed for the text meaning representations (TMRs) produced by the Ontological Semantic (OntoSem) general purpose syntactic-semantic analyzer. The goal of evaluation is not only to determine the quality of TMRs for given texts, but also to assign blame for various classes of errors, thus suggesting directions for continued work on both knowledge resources and processors. The paper includes descriptions of the OntoSem processing environment, the evaluation regime itself and results from our first evaluation effort.

Semantics in Action

The paper presents a concise description of a comprehensive approach to computational lexical semantics and focuses on the treatment of events. We reason about the semantic information that should be encoded in a lexicon entry to support the twin tasks of constructing Text Meaning Representations (TMRs) for input texts and generating texts off TMRs. As static knowledge sources cannot be expected to cover all textual inputs, we describe and illustrate how lexical entries can be changed dynamically to fit the textual context at processing time. On the very important issue of knowledge acquisition, our experience shows that determining the meaning of lexical items is not a trivial task for a team of human acquirers (who are, we believe, absolutely indispensable for the more complex decisions in lexical knowledge acquisition). We illustrate how one can overcome the subjectivity of acquirers partly through advanced methodology and partly by having the lexical-semantic model account for some of the combinatory and (semi-)productive principles of natural language.

Inconsistency as a diagnostic tool in a society of intelligent agents

OBJECTIVE To use the detection of clinically relevant inconsistencies to support the reasoning capabilities of intelligent agents acting as physicians and tutors in the realm of clinical medicine. METHODS We are developing a cognitive architecture, OntoAgent, that supports the creation and deployment of intelligent agents capable of simulating human-like abilities. The agents, which have a simulated mind and, if applicable, a simulated body, are intended to operate as members of multi-agent teams featuring both artificial and human agents. The agent architecture and its underlying knowledge resources and processors are being developed in a sufficiently generic way to support a variety of applications. RESULTS We show how several types of inconsistency can be detected and leveraged by intelligent agents in the setting of clinical medicine. The types of inconsistencies discussed include: test results not supporting the doctors hypothesis; the results of a treatment trial not supporting a clinical diagnosis; and information reported by the patient not being consistent with observations. We show the opportunities afforded by detecting each inconsistency, such as rethinking a hypothesis, reevaluating evidence, and motivating or teaching a patient. CONCLUSIONS Inconsistency is not always the absence of the goal of consistency; rather, it can be a valuable trigger for further exploration in the realm of clinical medicine. The OntoAgent cognitive architecture, along with its extensive suite of knowledge resources an processors, is sufficient to support sophisticated agent functioning such as detecting clinically relevant inconsistencies and using them to benefit patient-centered medical training and practice.

Resolving Paraphrases to Support Modeling Language Perception in an Intelligent Agent

When interacting with humans, intelligent agents must be able not only to understand natural language inputs but also to remember them and link their content with the contents of their memory of event and object instances. As inputs can come in a variety of forms, linking to memory can be successful only when paraphrasing relations are established between the meaning of new input and the content of the agents memory. This paper discusses a variety of types of paraphrases relevant to this task and describes the way we implement this capability in a virtual patient application.

OntoSem and SIMPLE: two multi-lingual world views

In this paper we compare programs of work that aim to develop broad coverage cross-linguistic resources for NLP: Ontological Semantics (OntoSem) and SIMPLE. The approaches taken in these projects differ in three notable respects: the use of an ontology versus a word net as the semantic substrate; the development of knowledge resources inside of as opposed to outside of a processing environment; and the development of lexicons for multiple languages based on a single core lexicon or without such a core (i.e., in parallel fashion). In large part, these differences derive from project-driven, real-world requirements and available resources -- a reflection of their being practical rather than theoretical projects. However, that being said, we will suggest certain preferences regarding the content and development of NLP resources with a view toward both short- and long-term, high-level language processing goals.

Operative strategies in ontological semantics

In this paper, we briefly and informally illustrate, using a few annotated examples, the static and dynamic knowledge resources of ontological semantics. We then present the main motivations and desiderata of our approach and then discuss issues related to making ontological-semantic applications feasible through the judicious stepwise enhancement of static and dynamic knowledge sources while at all times maintaining a working system.

OntoSem methods for processing semantic ellipsis

This paper describes various types of semantic ellipsis and underspecification in natural language, and the ways in which the meaning of semantically elided elements is reconstructed in the Ontological Semantics (OntoSem) text processing environment. The description covers phenomena whose treatment in OntoSem has reached various levels of advancement: fully implemented, partially implemented, and described algorithmically outside of implementation. We present these research results at this point -- prior to full implementation and extensive evaluation -- for two reasons: first, new descriptive material is being reported; second, some subclasses of the phenomena in question will require a truly long-term effort whose results are best reported in installments.