LDV FORUM Abstract Th is paper discusses a software design approach to allow interchange of linguistic data. It focuses on the modelling of the linguistic concepts represented in the data and describes the transfer between exchange formats as a multi-tier interpretation/generation. Th ese concepts are implemented in Smalltalk, a programming environment enabling fl exible conversion of data betw...

L Introduction We present here ELU, 1 all environment for research in computational linguistics, and, in particular, machine u'anslation. As its name indicates, ELU is one of the growing number of systems designed to employ unification as the principal computational mechanism; we shall mention below some respects in which it difl~rs from other such systems. In addition to investigations of MT t...

In order to produce efficient Natural Language Processing (NLP) tools, reliable linguistic resources are a preliminary requirement. When available for a given language, the resources are generally far below the expectations in terms of quality, coverage or usability. This paper presents a project whose ambition is to enhance the production capacities of linguistic resources through the creation...

This paper describes the design of a prototype machine translation system for a sublanguage of job advertis~nents. The design is based on the hypothesis that specialized linguistic subsystems may require special crmputational treatment and that therefore a relatively shallow analysis of the text may be sufficient for automatic translation of the sublanguage. This hypothesis and the desire to mi...

Therefore the linguistic contents of machine translation system always fluctuate, and make gradual progress. The system should be designed to allow such constant change and improvements. This paper explains the details of the transfer and generation stages of Japanese-to-English system of the machine translation project by the Japanese Government, with the emphasis on the ideas to deal with the...

The linguistic quality of a parallel treebank depends crucially on the parallelism between the source and target language annotations. We propose a linguistic notion of translation units and a quantitative measure of parallelism for parallel dependency treebanks, and demonstrate how the proposed translation units and parallelism measure can be used to compute transfer rules, spot annotation err...

Transfer-Driven Machine Translation (TDMT) [1, 2] is a translation technique developed as a research project at ATR Interpreting Telecommunications Research Laboratories. In TDMT, translation is performed mainly by a transfer module which applies transfer knowledge to an input sentence. Other modules, such as lexical processing, analysis, contextual processing and generation, cooperate with the...

The subject of this discussion consists selected concepts regarding the codematic foundations foreign-language learning and cybernetic systems communication. author focuses on processes controlling, regulating, directing structures at inter-individual level from teacher to learner. control process, coupled with process basic information transfer, supports strengthens it, both linguistic (supras...

This paper described recent activities of the Linguistic Data Consortium in the collection, annotation and distribution of language data the developments of tools and standards for using that data, the creation of metadata to facilitate the search for linguistic resources.

Although it prefigures many advances in linguistic theory, the scholarship of nineteenth century scholar Mikołaj Kruszewski is today largely forgotten. In these papers I hope to rectify this situation somewhat by introducing Kruszewski’s insights to modern discourse on phonology. In addition to a detailed summary of Kruszewski’s major work, An Outline of Linguistic Science (Očerk Nauki O Jazyke...