XeLDA v2.0. (Tools).Xerox Multilingual Knowledge Management Solutions have released version released version - release two of its linguistic engine, Xerox Linguistic Development Architecture (XeLDA). XeLDA consists of a set of natural language processing Natural language processing Computer analysis and generation of natural language text. The goal is to enable natural languages, such as English, French, or Japanese, to serve either as the medium through which users interact with computer systems such as services providing a set of tools for application developers and integrators enabling a range of text processing functions in up to 17 languages. This allows companies to incorporate a range of processes into their applications based on accurate analysis and comprehension. Comment: XeLDA is a set of tools which can be incorporated into applications and provide text processing in several different languages by applying linguistic theory and science. Potential applications include text analysis, enhanced search capacities, terminology extraction Terminology extraction, term extraction, or glossary extraction, is a subtask of information extraction. The goal of terminology extraction is to automatically extract relevant terms from a given corpus. , authoring tools, translation processes or Multilingual Document Management. XeLDAC services support Western European languages (Dutch, English, French, German, Italian, Portuguese, Spanish), several Eastern Europe languages (Hungarian, Polish, Russian) and Northern Europe languages (Danish, Finnish, Norwegian -Bokmal and Nynorsk-, Swedish). Version 2.6 includes a new sentence segmentation service, enhanced performance, and the capability to generate results in XML XML in full Extensible Markup Language. Markup language developed to be a simplified and more structural version of SGML. It incorporates features of HTML (e.g., hypertext linking), but is designed to overcome some of HTML's limitations. format, Chinese and Czech language support and availability of C++/Java APIS Apis (ā`pĭs), in Egyptian religion, sacred bull of Memphis, said to be the incarnation of Osiris or of Ptah. His worship spread throughout the Mediterranean world and was particularly important during the time of the Roman Empire. . Product features include: Language identification: recognises the language used by a selected text Sentence segmentation: divides a text into sentences. Tokenisation: breaks down the selected text into lexemes. Morphological analysis: provides the normalised normalised - normalisation form and potential pan of speech categories for each word identified during tokenisation. Part of speech disambiguation dis·am·big·u·ate tr.v. dis·am·big·u·at·ed, dis·am·big·u·at·ing, dis·am·big·u·ates To establish a single grammatical or semantic interpretation for. : finds the correct pan of speech category of a word according to its context within a text. Noun phrase extraction: identifies a sequence of words that behave together as a noun. Contextual dictionary lookup: retrieves a word context and uses this context to find the correct entry in the dictionary. Idiomatic expression recognition: recognises idiomatic expressions in a text. Relational morphology (prototype): groups words according to their derivational family. www.mkmsxerox.com |
|
||||||||||||||||
Printer friendly
Cite/link
Email
Feedback
Reader Opinion