Abstract:
The paper discusses the general architecture of NLU-systems. We focus on three main subjects: target information technology and target knowledge representation language; processing levels interaction and integration; role and proportion of rule-based and corpus-based methods.
Keywords:
информационный анализ делового текста, компоненты анализатора, архитектура анализатора, целевая технология, целевой язык, фактографическая информация.