Revision as of 01:14, 3 March 2010 edit Spencerk (talk \| contribs) Autopatrolled, Extended confirmed users, Pending changes reviewers 4,233 edits →History ← Previous edit		Revision as of 02:00, 3 March 2010 edit undo Spencerk (talk \| contribs) Autopatrolled, Extended confirmed users, Pending changes reviewers 4,233 edits No edit summary Next edit →
Line 13: ==History== Prototype Nl interfaces had already appeared in the late sixties and early seventies. <ref name="edin"> Natural Language Interfaces to Databases – An Introduction, I. Androutsopoulos, G.D. Ritchie, Line 57: * [http://www.inbenta.com/sitesearch Semantic Search Engine with Natural language processing capabilities] ==~~Criticism~~Challenges== Natural language interfaces have in the past led users to anthropomorphize the computer, or at least to attribute more intelligence than is warranted to it. This leads to unrealistic expectations of the capabilities of the system on the part of the user. Such expectations will make it difficult to learn the restrictions of the system if they attribute to much capability to it, and they will lead to disappointment when the system fails to perform as expected. A [http://arxiv.org/abs/cmp-lg/9503016 1995 paper] titled 'Natural Language Interfaces to Databases – An Introduction', describes some challenges:<ref name="edin"/> Modifier attachment The request “List all employees in the company with a driving licence” is ambiguous unless you know companies can't have drivers licences. Conjunction and disjunction “List all applicants who live in California and Arizona.” is ambigious unless you know that a person can't live in two places at once. [[Anaphora resolution]] - resolve what a user means by 'he', 'she' or 'it', in a self-referential query. == See also == [[Noisy text]]

Natural-language user interface: Difference between revisions