Various Representations Of Text Proposed For Eurotra
نویسندگان
چکیده
We in t roduce severa l genera l no t ions concerning the texts and the particularities of text processing on a computer support, in relation to some problems which are specific to M(A)T. And we present the solution we have proposed for the duration of the EUROTRA project.
منابع مشابه
Parsing Danish Text in EUROTRA
The machine translation project Eurotra is described as a multi language modular translation system with 9 monolingual analysis modules, 72 bilingual transfer modules, and 9 monolingual synthesis modules. The analysis module for Danish is described as a 3 step parser with structure generation rules for immediate constituent structure, syntactic structure, and semantic structure, and translation...
متن کاملEurotra: an Assessment of the Current State of the Ec's Mt Programme
In this talk we are going to give a view of what is happening, and is likely to happen in the 'Eurotra' programme, and its surrounding initiatives. To do this, and to make sure the paper has some relevance beyond the immediate future, we will also sketch out some of the history of the project, and describe the results that have been achieved. We will also give some pointers to the technical, an...
متن کاملA Joint Semantic Vector Representation Model for Text Clustering and Classification
Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...
متن کاملRepresentational Issues within Eurotra
Machine translation of subordinate clauses, whether finite or non-finite, poses a series of problems within representational issues. In £ U R O T R A this subject has recently been investigated for complements as well as for modifiers to verbal, nominal, adjectival, and prepositioned heads. Some of the problems encountered during these investigations will be addressed in this paper, with a part...
متن کاملLarge Lexical European Projects and the MultilinguaI Aspect
We aim at providing an overview and a comparison of multilingual and Machine Translation (MT) related issues that emerge and that are handled within the major European projects in the lexical area (ET-7, Acquilex I and If, Multilex, Genelex, ET-10 Semantic Analysis of Cobuild, ET-10 Collocations, ET-10 Statistical Text-corpora based complements for Eurotra, Delis, Eurolang and Eagles), most of ...
متن کامل