this paper, contains literal, metonymic, metaphorical, and anomalous semantic relations. The assertion-based class of relations are described in greater length in Fass (1989a)

Abstract not found

Abstract not found

. In knowledge-based machine translation (KBMT), the lexicon can be specified and acquired only in close connection with the specification and acquisition of the world model (ontology) and the specification of the text meaning representation (interlingua) language. The former supplies the atoms for the specification of text meaning and provides world knowledge to support the inference processes necessary for a variety of disambiguation and meaning assignment operations. The latter is necessary for the formulation of the semantic zone of the lexicon entries, which can be viewed as containing the static building blocks of the text meaning representation. This is the view taken in the Mikrokosmos KBMT project. 1. Introduction. Over the past decade, the number and diversity of experiments in Knowledge-Based Machine Translation (KBMT) has grown significantly (cf. Nirenburg et al., 1987; Cullingford and Onyshkevych, 1987; Carbonell et al., 1992, or Nyberg and Mitamura, 1992; Niren...

In this paper we present one aspect of our presents a clear case of where general as well as specific research on machine translation (MT): defining the re- real world knowledge should assist in eliminating inap- lation between the interlingua (IL) and a knowledge representation (KR) within an MT system. Our interest lies in the translation of natural language (NL) sentences where the "message" contains a spatial relation in particular, where the sentence conveys information about the location or path of physical entities in the real, physical world. We explore several arguments for clarifying the source of constraints on the particular IL structures needed to translate these sentences.

Components come in a variety of formats, designs and implementations. Components can be designed to work together or their designs can be totally incompatible. This influences greatly the amount and kind of composition work that is to be done. In this work, we build on the work of architectural description languages to improve current visual component composition environments. This is done using the concept of composition patterns. A composition pattern describes an interaction between a set of roles using an extended sequence chart. It serves as a bridge between the design and the implementation. We further propose a component documentation using the same kind of extended sequence charts. The concept of composition patterns lifts the abstraction level of current composition techniques to the same level of the components. I.e. composition patterns are first class objects that can be defined, stored and reused independently of the components. We further develop and implement algorithms to perform automatic compatibility checking based on finite automata theory. We also developed tool support that gives

: We describe the use of an LCS-based semantics for question-answering exercises in foreign language training. We start by reviewing the LCS model and show how this representation can be used to support a question answering lesson as well as a limited domain discourse. An authoring tool for entering the relevant semantic knowledge is also described. 1 Introduction The chapters in this book result from a workshop which presented a number of stateof -the-art projects in Intelligent Computer Aided Language Learning (ICALL). At that workshop, several different speakers stated that the study of syntactic processing was at a mature enough state that it could be reliably used as a basis for tutoring systems. Semantic knowledge, however, was deemed to be less well understood and not reliable for use outside of extremely limited domains such as graphics microworlds or "adventure game" level discourse. Further, authoring of semantic knowledge was dismissed as not currently available. It is our ...

Knowledge-based machine translation can be viewed as the problem of extracting and representing the meaning of a text and generating a translation in a target language using the meaning representation. Meaning extraction requires the integration of information present explicitly in a text with common sense and domain knowledge given to the system. Thus, integrating linguistic knowledge of each language with general world knowledge is a central problem in machine translation, especially when more than two languages are involved. In this article we consider the design of a meaning representation that enables language-specific lexicons to share knowledge with a language-independent world model. We illustrate how the underlying core meaning representation can be enhanced in three different ways to arrive at lexical, ontological, and text meaning representations. The meaning representations presented here have been implemented in the Mikrokosmos machine translation system and used to repres...

Abstract not found

This paper describes a multi-level design, i.e., a non-uniform approach to interlingual machine translation (MT), in which distinct representational languages are used for different types of knowledge. We demonstrate that a linguistically-motivated "division of labor" across multiple representation levels has not complicated, but rather has readily facilitated, the identification and construction of systematic relations at the interface between each level. Our approach assumes an interlingua derived from the lexical semantics and predicate decomposition approaches of Jackendoff (1983; 1990) and Levin and Rappaport-Hovav (1995a; 1995b). We describe a model of interpretation and representation of natural language sentences which has been implemented as part of an interlingual MT system called PRINCITRAN.