Many applications, today, work with natural language,
using techniques such as information extraction,
information retrieval, semantic search.
For this reason require algorithms that process
human language written and spoken.
Some steps of Natural Language Processing (NLP) include
text normalization, tokenization, stop words elimination,
stemming, Part Of Speech tagging, lemmatization.
Additional steps, such as Word Sense Disambiguation (WSD)
and Named Entity Recognition (NER), are geared to enriching
the text with semantic information.
The purpose of Collector and thus
Lexical Browser is precisely to create a service
that, given a lexeme, provides all the syntactic and semantic
information collected by a set of lexical resources, semantic resources and from Web.
Language resources used are both static as Wordnet (to quote the most popular),
and dynamic as a Web Search Service Search Service and Wiki.
« Show less