A situated ontology is a world model used as a computational resource for solving a particular set of problems. It is treated as neither a "natural" entity waiting to be discovered nor a purely theoretical construct. This paper describes how a semantico-pragmatic analyzer, Mikrokosmos, uses knowledge from a situated ontology as well as from language-specific knowledge sources (lexicons and microtheory rules). Also presented are some guidelines for acquiring ontological concepts and an overview of the technology developed in the Mikrokosmos project for large-scale acquisition and maintenance of ontological databases. Tools for acquiring, maintaining, and browsing ontologies can be shared more readily than ontologies themselves. Ontological knowledge bases can be shared as computational resources if such tools provide translators between different representation formats. 1 A Situated Ontology World models (ontologies) in computational applications are artificially constructed entities. ...

In the field of natural language processing (NLP) there is now a consensus that all NLP systems that seek to represent and manipulate meanings of texts need an ontology, that is a taxonomic classification of concepts in the world to be used as semantic primitives. In our continued efforts to build a multilingual knowledge-based machine translation (KBMT) system using an interlingual meaning representation, we have developed an ontology to facilitate natural language interpretation and generation. The central goal of the Mikrokosmos project is to develop a computer system that produces a comprehensive Text Meaning Representation (TMR) for an input text in any of a set of source languages. Knowledge that supports this process is stored both in language-specific knowledge sources (such as a lexicon) and in an independently motivated, language-neutral ontology of concepts in the world.

Abstract. Word sense disambiguation continues to be a difficult problem in natural language pro-cessing. Current methods, such as marker passing and spreading activation, for applying world knowledge in the form of selectional preferences to solve this problem do not make effective use of available knowledge. Moreover, their effectiveness decreases as the knowledge is made richer by acquiring more and more conceptual relationships. Effective resolution of word sense ambiguities requires inferring the dynamic context in processing a sentence in order to find the right selectional preferences to be applied. In this article, we propose such an inference operator and show how it finds the most specific context to resolve word sense ambiguities in the Mikrokosmos semantic ana-lyzer. Our method retains its effectiveness even in a rich, large-scale knowledge base with a high degree of connectivity among its concepts. 1. Disambiguation in Context Word sense disambiguation continues to be a difficult problem for programs that process natural language. The goals of word sense resolution methods are: (a) to select as small a subset of possible senses of a word as possible, ideally just one sense, and (b) to select the best sense(s) given all the knowledge available to the system, including the dynamic context in processing the text. The most common methods for resolving word sense ambiguities are based on statistical collocations or selectional preferences (for a recent survey, see Guthrie et al, 1996) between pairs of word senses. Often, individual selectional preferences applicable to a word are not strong enough to exclude all but one sense of the word. The real power of word sense selection seems to lie in the ability to constrain the possible senses of a word based on selections made for other words in the dynamic context. Although it is a truism that context plays a significant role in sense disambiguation, computational models have not demonstrated the effectiveness of modeling context for resolving word senses in a large-scale NLP system.

. Word sense disambiguation continues to be a di#cult problem in machine translation #MT#. Current methods either demand large amounts of corpus data and training or rely on knowledge of hard selectional constraints. In either case, the methods have been demonstrated only on a small scale and mostly in isolation, where disambiguation is a task by itself. It is not clear that the methods can be scaled up and integrated with other components of analysis and generation that constitute an end-to-end MT system. In this paper, we illustrate how the Mikrokosmos Knowledge-Based MT system disambiguates word senses in real-world texts with a very high degree of correctness. Disambiguation in Mikrokosmos is achieved by a combination of #i# a broad-coverage ontology with many selectional constraints per concept, #ii# a large computational-semantic lexicon grounded in the ontology, #iii# an optimized search algorithm for checking selectional constraints in the ontology, and #iv# an e#cie...

In this paper we describe a range of techniques used at NMSU CRL for accelerating the development of MT systems. These techniques enable semi-automatic development of a number of components of a multilingual MT system, thereby enabling rapid deployment of MT capabilities in a new language. First, we describe the core multi-engine, multilingual architecture that enables the different techniques to be rapidly integrated to build an MT system. We show how off-the-shelf components were used in this architecture for fast development. Then we illustrate a set of techniques for semi-automatic acquisition of static resources: (a) automatic induction of grammars, (b) corpus-based acquisition of bilingual glossaries, and automatic acquisition of semantic lexicons through (c) lexical rules and (d) reversal of analysis lexicons to generation lexicons. Finally we describe an automatic testing environment that enables rapid validation of automatically acquired resources. 1 Rapid Development Techniques Static knowledge sources — grammars, lexicons, world knowledge bases — are the most time-consuming concerns in any rule-based machine translation system. It is, therefore, imperative to find ways of speeding up the creation and updating of high-quality, useful static knowledge sources. It is equally imperative to

9. Bibliography

Adjectives constitute a challenging issue for NLP applications. From a syntactic viewpoint, they can be predicative or attributive. From a semantic viewpoint, their sense can vary depending on the context in which they appear. In this paper we present an overview on the lexical semantics of adjectives in Natural Language Processing, followed by the presentation of the papers included in this proceeding.

In this paper, we show how a computational semantic approach is best fitted to address the translation of highly isolating languages. We use Chinese as an example and present the overall process of translation from Chinese to English, within the framework of Knowledge-Based Machine Translation (KBMT), using an overt semantics while de-emphasizing syntax. We focus here on two particular tasks: Word Sense Disambiguation (WSD) and compound translation. 1

Introduction Our approach to the lexicon has been driven by both theoretical and practical concerns. From a theoretical viewpoint, we are interested in capturing the core meanings of texts. We believe that lexical semantics is a crucial knowledge component of text meaning derivation, as it describes lexical meanings in their composition and combination 1 properties. A major tenet of our methodology is a separation of what is language-dependent and what is universal in semantic speci#cations. To help in determining this, our research methodology centrally includes a cross-linguistic perspective. From a practical standpoint, our lexicons are designed to support machine translation #MT# systems, in which the issue of multilinguality is clearly central. Theoretical and practical concerns are combined into the Mikrokosmos # #K # approach, where, within the paradigm of knowledge-based machine translation #KBMT#, we build lexicons for di#erent natural l

In this paper, we address representation issues of Chinese nominals. In particular, we look at lexical rules as a conceptual tool to link forms with the same semantics as is the case between nominalisations and the forms they are derived from. We also address Chinese compounds, illustrating how to recover implicit semantic relations in nominal compounds. Finally, we show how to translate Chinese non finals within a knowledge-based framework.