摘要 |
The invention relates to a system for extracting information from a natural language text. According to the invention, the extraction method consists in: encoding the words from the text by comparing said words with the contents of a lexicon of empty words (essentially articles, prepositions, conjunctions and verbal auxiliaries); and, subsequently, identifying noun phrases by searching for groups of encoded words that adhere to the pre-defined syntactic rules from among the subsets from the series of encoded words thus obtained. |