The development of natural language interfaces to Artificial Intelligence systems is dependent on the representation of knowledge. A major impediment to building such systems has been the difficulty in adding sufficient linguistic and conceptual knowledge to extend and adapt their capabilities. This difficulty has been apparent in systems which perform the task of language production, i. e. the...

It is well known that two complementary learning modules are important to achieve human-level language understanding: one gradually acquires structured representations of knowledge from language, the other quickly learns the episodic memory composed of individual knowledge. In this paper, we suggest a new machine learning model which combines symbolic and neuronal approaches to construct the co...

Many intelligent agents need knowledge and information to support their reasoning and problem solving. The World Wide Web is a vast, open, accessible and free source of knowledge, but virtually all of it is encoded as natural language text – a form difficult for most agents to directly understand. We describe initial work on adapting a mature language understanding agent to process Web text and...

A framwork for Natural Language Generation (NLG) is described, that can be used with arbitrarily structured knowledge sources (for example a database). It is built around three layers of domain knowledge representation , supporting diierent tasks. The beneet of this approach is that a given representation can be used as input to NLG rather than a redundant representation that has to be maintain...

Medical natural language understanding basically aims at representing the contents of medical texts in a formal, conceptual representation. The understanding process itself increasingly relies on a body of domain knowledge, generally expressed in the same conceptual formalism. The design of such a conceptual representation is a key knowledge-acquisition issue. When representing knowledge, the m...

In recent years, there has been renewed interest in the NLP community in genuine language understanding and dialogue. Thus the long-standing issue of how the semantic content of language should be represented is reentering the communal discussion. This paper provides a brief “opinionated survey” of broadcoverage semantic representation (SR). It suggests multiple desiderata for such representati...

This working note sketches out, in a rather skeletal form, a model of language understanding using the knowledge representation language KM. In this model, KM “prototypes” encode stereotypical expectations about the world, and language understanding involves constructing a scene from prototypes which best matches (a possible interpretation of) the input text. As a starting point towards this, w...

purpose: the present study seeks to explore the effects of general language proficiency, text readability, and medical knowledge on comprehending medical texts. material & method: 63 medical students in the second year of their study were randomly selected from the english language classes. they answered 100 multiple-choice questions on grammar and vocabulary to establish the level of language ...

Guideline and protocol representation languages have reached a level of complexity where auxiliary methods are needed to support the authoring of protocols in the particular language. Several approaches and methods exist that claim high knowledge about both, the medical context and the formal requirements. Therefore, we need knowledge-based methods to facilitate the human plan designer and crea...

Natural Language Generation Marcel O. Fr ohlich 1 and Reind P. van de Riet 2 Abstract. A framwork for Natural Language Generation (NLG) is described, that can be used with arbitrarily structured knowledge sources (for example a database). It is built around three layers of domain knowledge representation, supporting di erent tasks. The bene t of this approach is that a given representation can...