To avoid forcing searchers to memorize Boolean or other query languages, some systems allow them to type in a question, and use that as the query: this is known as "Natural Language Processing" (NLP). The simplest processing just removes stopwords and uses a vector search or other statistical approach. Some sophisticated systems try to extract concepts using linguistic analysis, and match those against concepts extracted by the indexer. Others try to categorize the form of the question and use it to define the query, so "who is" questions are not treated the same as "how many" or "why": a good example of this approach is the AskJeeves system.

• Asking Naturally: Vendors of natural language query tools hope to attract enterprise customers Knowledge Management; August 2001 by Peter Ruber
  Balanced coverage of the possible value of natural language searching compared with strict Boolean and SQL queries. Mentions AskJeeves, AnswerLogic and iPhrase, with some customer comments.
  
  
• Not by Words Alone: The Trend to Improve Information Retrieval LexiQuest White Paper by Sue Feldman, DataSearch Labs (registration required)
  Describes how linguistic tools can improve searches by reducing ambiguity and providing context.
  
  
• Natural Language Processing Using Very Large Corpora edited by Susan Armstrong, et al. November 1999, Kluwer, 0-7923-6055-9, $128.
  Current theory and practice for searching and translating in the very large collections (millions of documents) now available. If you buy it from FatBrain or Amazon using these links, you'll support the searchtools site.
  
  
• Natural Language Information Retrieval edited by Tomek Strzalkowski, July 1999 Kluwer ISBN 0792356853, $144
  New, comprehensive work on the topic, designed for researchers and practitioners. If you it from Amazon or FatBrain using these links, you'll support the searchtools site.
  
  

• NLP Meets the Jabberwocky: Natural Language Processing in Information Retrieval Susan Feldman, Online, May 1999. This is a wonderful introduction to the concepts and issues of using NLP for searching. It does assume search engines that already do more than simple Boolean retrieval.

• Covered in Modern Information Retrieval Ricardo Baeza-Yates & Berthier Ribero-Neto, Addison-Wesley Longman, May 1999, ISBN 020139829x, $50, specifically in the User Interface chapter. Get the book from Amazon or FatBrain.com and we'll get an affiliate fee.

• Information Retrieval & Natural Language Processing - an excellent annotated listing of useful sites and information.
  
  
• Implemented in the InQuery search engine from the Center for Intelligent Information Research,
  
  
• Implemented in the Inxight LinguistX package.
  

• Information Retrieval Research
• Cross-Language Information Retrieval

  
  Page Updated 2002-03-29