This thesis proposes a strongly lexicalist approach to machine translation and applies it to the translation of spatial prepositions and prepositional expressions between English and Spanish. Bilingual contrastive knowledge resides solely in the bilingual lexicon and is structured in the form of correspondences between sets of source and target language lexemes related through indices. The resulting architecture maximizes the independence of the monolingual and bilingual components. This independence is demonstrated by developing a grammar of Spanish which is significantly different in its constructions from its analogous English grammar. In particular, relative clauses are analysed through a single rule that allows gaps in subject position, while clitic climbing and doubling are handled through mechanisms not normally found in grammatical descriptions of English. Bilingual lexical rules, in conjunction with the bilingual lexicon, constitute a single, motivated and well defined mechani...

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.

Abstract not found

Abstract not found

of the International Conference on Computational Science. The contributors to the workshop represent, in their backgrounds, the diversity of fields upon which the focus of the event draws. As a result, this paper aims not only to introduce the accepted papers, but also to provide a background that will be accessible to researchers in the various fields, and to sit each work into a coherent context. 1

This paper describes a new Cornell University course serving as a non-programming introduction to computer science, with natural language processing and information retrieval forming a crucial part of the syllabus. Material was drawn from a wide variety of topics (such as theories of discourse structure and random graph models of the World Wide Web) and presented at some technical depth, but was massaged to make it suitable for a freshman-level course. Student feedback from the first running of the class was overall quite positive, and a grant from the GE Fund has been awarded to further support the course's development and goals.

This paper is merely an attempt to build up a canvas of issues, on which further discussion is needed.

This work or any part thereof has not previously been presented in any form to the University or to any other body whether for the purposes of assessment, publication or for any other purpose (unless otherwise indicated). Save for any express acknowledgments, references and/or bibliographies cited in the work, I confirm that the intellectual content of the work is the result of my own efforts and of no other person. The right of Constantin Orăsan to be identified as author of this work is asserted in accordance with ss.77 and 78 of the Copyright, Designs and Patents Act 1988. At this date copyright is owned by the author.

Inheritance networks are a type of semantic network which represent both strict (classical implication) and defeasible (non-classical) relationships among entities. We present an established approach to defeasible reasoning which defines inference in terms of the construction of paths through a network. Much of literature on inheritance is concerned with specifying the most "intuitive" system of path construction. However, when considering a fundamental feature of these approaches---the status accorded to redundant links---we find that topological considerations espoused in the literature are insufficient for determining the valid inferences of a network. This implies that the "intuitiveness" of a particular method depends upon the domain being represented. Though Touretzky has demonstrated that it is unsound in some cases, the path-preference algorithm known as shortest path reasoning, is actually the most intuitive algorithm to use when reasoning about the inheritance network which r...

Effects of ellipsis and anaphor resolution on proximity searching in a text database are analyzed. Anaphora and ellipses are classified into proper names and common nouns of basic words, compound words, and phrases. 28 queries for which document relevance of data was available, were run in a newspaper database of 55.000 articles. The resolution of ellipses and anaphora was done manually. Resolution was most relevant for person names (both anaphora and ellipses) and other proper name phrases (ellipses) and only marginal in other keyword categories. Recall improvement due to resolution decreased when query exhaustivity grew and was greater in sentence than paragraph searches.