Abstract not found

This paper describes techniques for automatic construction of dictionaries for use in large-scale foreign language tutoring (FLT) and interlingual machine translation (MT) systems. The dictionaries are based on a language-independent representation called lexical conceptual structure (LCS). A primary goal of the LCS research is to demonstrate that synonymous verb senses share distributional patterns. In this paper, we show how the syntax-semantics relation can be used to develop a lexical acquisition approach that contributes both toward the enrichment of existing online resources and toward the development of lexicons containing more complete information than is provided in any of these resources alone. We start by describing the structure of the LCS and showing how this representation is used in FLT and MT. We then focus on the problem of building LCS dictionaries for large-scale FLT and MT. First, we describe authoring tools for manual and semi-automatic construction of LCS dictionaries; we then present a more sophisticated approach that uses linguistic techniques for building word defmitions automatically. These techniques have been implemented as part of a set of lexicon-development tools used in the MILT FLT project (Dorr et al., 1995; Sams, 1995; Weinberg et al., 1995) and in the PRINCITRAN MT project (Dorr et al., 1995b).

: 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 ...

This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

Communication using natural language is remarkably e cient, by allowing reuse (through the use of generative devices) of a nite vocabulary to describe a potentially innite set of situations. This vocabulary reuse contributes to words having many related senses (polysemy). Further, meanings can be relatively vague or precise � in other words, varying in their degree of speci cation of meaning. I suggest that these problems can be addressed by developing a knowledge representation which makes explicit the notion of granularity. As the grain size changes, we may fold certain distinctions, or split meanings more nely. In this paper, I formalize a theory of granularity and demonstrate how it can be applied to problems of meaning representation. Such a theory requires a world model which provides a rich sortal di erentiation of entities based on the distinctions made by natural language, including the representation of meronymic structure and rei-cation. Granularity will be represented in terms of structural operations de ned as abstractions. I illustrate how this applies to problems of polysemy and vagueness in nominalizations, where splitting and folding of meanings are particularly evident. 1

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.

Choosing the wrong word in a machine translation or natural language generation system can convey unwanted connotations, implications, or attitudes. The choice between near-synonyms such as error, mistake, slip, and blunder — words that share the same core meaning, but differ in their nuances — can be made only if knowledge about their differences is available. We present a method to automatically acquire a new type of lexical resource: a knowledgebase of near-synonym differences. We develop an unsupervised decision-list algorithm that learns extraction patterns from a special dictionary of synonym differences. The patterns are then used to extract knowledge from the text of the dictionary. The initial knowledge-base is later enriched with information from other machine-readable dictionaries. Information about the collocational behavior of the near-synonyms is acquired from free text. The knowledge-base is used by Xenon, a natural language generation system that shows how the new lexical resource can be used to choose the best near-synonym in specific situations. 1. Near-synonyms Near-synonyms are words that are almost synonyms, but not quite. They are not fully inter-substitutable, but vary in their shades of denotation or connotation, or in the components

Abstract not found

In this paper, we report our work on the creation of a number of lexical resources that are crucial for an interlingua based MT from English to other languages. These lexical resources are in the form of sub-categorization frames, verb knowledge bases and rule templates for establishing semantic relations and speech act like attributes. We have created these resources over a long period of time from Oxford Advanced Learners ’ Dictionary (OALD) [1], VerbNet [2], Princeton WordNet 2.1 [3], LCS database [4], Penn Tree Bank [5], and XTAG lexicon [6]. On the challenging problem of generating interlingua from domain and structure unrestricted English sentences, we are able to demonstrate that the use of these lexical resources makes a difference in terms of accuracy figures. 1.