SAIL develops multilingual language technology (incl. English, German, Russian, Arabic, Japanese, Chinese) like machine translation, information retrieval, fact extraction and speech applications. Therefore using Unicode is absolutely mandatory for our company.

One of the central tasks is to compare texts with lexical resources and manipulate texts like the lookup of words in databases and the translation of texts into other languages.

The tools and functionalities we need the following:
- a Unicode Database with a specific linguistic data model
- import/export functionality combined with Unicode enabled interfaces
- using OLIF, a lexicon exchange format developed in European Community projects
- Unicode Text handling and analysis
- DB Lookup of terminolgy in text documents
- text handling format in XML / Unicode
- NLP tools (lemmatisers, machine translation, memories) in Unicode
- Unicode text generation (generate target language texts in Unicode)

The conclusion is that NL applications in Unicode need consistent Unicode support in databases, text processing, GUIs (Web and Editor) and XML support.