The information retrieval (IR) technique gives a set of documents based on the query. For example, when we do a google search, we supply a query string to the search engine, and then based on the search engine algorithm, it returns a set of web documents link to us. The mentioned example is one way to understand web information retrieval from the information system.
The information extraction (IE) techniques give a fact about the document from the repository of documents or the information system. It also requires an understanding of the entities, syntax, and semantics of unstructured data.
Suppose we want to know the stock price of Google and let us consider that we have received a set of web documents link from a typical search engine. So our next task is to identify the entity. Here, the entity is an organization called Google and associated stock value. The stock value must be a decimal with positive or negative signs and so on. For extracting values, we should understand semantics, such as in which format a web document keeps stock name and value.
These two terms, such as information retrieval and information extraction, are related to each other. The information retrieval process gives relevant documents, and the extraction process provides meaningful information from the web documents.
199 total views, 1 views today
