Natural Language Processing in Textual Information Retrieval and Related Topics

"Natural Language Processing" (NLP) as a discipline has been developing for many years. It was formed in 1960 as a sub-field of Artificial Intelligence and Linguistics, with the aim of studying problems in the automatic generation and understanding of natural language.

At first its methods were widely accepted and successful. However, when applied in controlled environments and with a generic vocabulary, many problems arose. Among those problems were polysemy and synonymy.

In recent years contributions to this field have improved substantially, allowing for the processing of huge amounts of textual information with an acceptable level of efficacy. An example of this is the application of these techniques as an essential component in web search engines, in automated translation tools or in summary generators [Baeza-Yates, 2004].

This article aims to review the main characteristics of natural language processing techniques, focusing on its application in information retrieval and related topics Specifically, in the second section we will study the different problems in automatic natural language processing; in the third section we will describe the key methodologies of NLP applied in information retrieval; and in the fourth section we will state several fields of research related to information retrieval and natural language processing; finally we present the conclusions and an annexe (Annexe 1) showing some of the particular aspects of NLP in Spanish.