Natural-language user interface: Difference between revisions

Revision as of 20:18, 25 August 2021

Latest revision as of 19:15, 27 July 2025

(15 intermediate revisions by 12 users not shown)

Line 1:

{{short description|Type of computer human interface}}{{Outdated|date=February 2025}}

'''Natural-language user interface''' ('''LUI''' or '''NLUI''') is a type of [[User interface|computer human interface]] where linguistic phenomena such as verbs, phrases and clauses act as UI controls for creating, selecting and modifying data in software applications.

In [[interface design]], natural-language interfaces are sought after for their speed and ease of use, but most suffer the challenges to [[natural language understanding|understanding]] wide varieties of [[semantic ambiguity|ambiguous input]].<ref>Hill, I. (1983). "Natural language versus computer language." In M. Sime and M. Coombs (Eds.) Designing for Human-Computer Communication. Academic Press.</ref>

Natural-language interfaces are an active area of study in the field of [[natural-language processing]] and [[computational linguistics]]. An intuitive general natural-language interface is one of the active goals of the [[Semantic Web]].

Text interfaces are "natural" to varying degrees. Many formal (un-natural) programming languages incorporate idioms of natural human language. Likewise, a traditional [[keyword search]] engine could be described as a "shallow" natural-language user interface.

==Overview==

InA natural-language search engine would in theory find targeted [[question answering|answers to user questions]] (as opposed to a keyword search). For example, when confronted with a question of the form 'which [[United States|U.S.]] state has the highest [[income tax]]?', conventional search engines ignore the question and instead search on the [[index term|keywords]] 'state', 'income' and 'tax'. Natural-language search, on the other hand, attempts to use natural-language processing to understand the nature of the question and then to search and return a subset of the web that contains the answer to the question. If it works, results would have a higher relevance than results from a keyword search engine, due to the question being included.{{Citation needed|date=October 2015}}

==History==

Line 15 ⟶ 20:

*[[SHRDLU]], a natural-language interface that manipulates blocks in a virtual "blocks world"

*''Lunar'', a natural-language interface to a database containing chemical analyses of [[Apollo- 11]] moon[[Moon rocks]] by [http://parsecraft.com/ William A. Woods].

*''Chat-80'' transformed English questions into [[Prolog]] expressions, which were evaluated against the Prolog database. The code of Chat-80 was circulated widely, and formed the basis of several other experimental Nl interfaces. An online demo is available on the LPA website.<ref>{{cite web|url=http://www.lpa.co.uk/pws_dem5.htm|title=Chat-80 demo|access-date=29 January 2018|archive-url=https://web.archive.org/web/20161111194841/http://www.lpa.co.uk/pws_dem5.htm|archive-date=11 November 2016|url-status=dead|df=dmy-all}}</ref>

*[[ELIZA]], written at MIT by Joseph Weizenbaum between 1964 and 1966, mimicked a psychotherapist and was operated by processing users' responses to scripts. Using almost no information about human thought or emotion, the DOCTOR script sometimes provided a startlingly human-like interaction. An online demo is available on the LPA website.<ref>{{cite web|url=http://www.lpa.co.uk/pws_dem4.htm|title=ELIZA demo|access-date=29 January 2018|archive-url=https://web.archive.org/web/20161126102154/http://www.lpa.co.uk/pws_dem4.htm|archive-date=26 November 2016|url-status=dead|df=dmy-all}}</ref>

Line 54 ⟶ 59:

* ''Medical, disabilities'', many people have difficulty typing due to physical limitations such as repetitive strain injuries (RSI), muscular dystrophy, and many others. For example, people with difficulty hearing could use a system connected to their telephone to convert a caller's speech to text.

* ''Embedded applications'', some new cellular phones include C&C speech recognition that allow utterances such as "call home". This may be a major factor in the future of automatic speech recognition and [[Linux]].

* ''[[Software development]]'': An [[integrated development environment]] can embed natural-language interfaces to help developers.<ref>{{Cite book |doi=10.1109/ase.2011.6100076|arxiv=1205.6361|isbn=978-1-4577-1639-3|chapter=Querying source code with natural language|title=2011 26th IEEE/ACM International Conference on Automated Software Engineering (ASE 2011)|pages=376–379|year=2011|last1=Kimmig|first1=Markus|last2=Monperrus|first2=Martin|last3=Mezini|first3=Mira|s2cid=6898947}}</ref>

Below are named and defined some of the applications that use natural-language recognition, and so have integrated utilities listed above.

Line 64 ⟶ 68:

===Wolfram Alpha===

{{main|Wolfram Alpha}}

Wolfram Alpha is an online service that answers factual queries directly by computing the answer from structured data, rather than providing a list of documents or web pages that might contain the answer as a [[search engine]] would.<ref>{{cite news |url=https://www.theguardian.com/technology/2009/mar/09/search-engine-google |title=British search engine 'could rival Google' |last=Johnson |first=Bobbie |date=2009-03-09 |work=[[The Guardian]] |access-date=2009-03-09}}</ref> It was announced in March 2009 by [[Stephen Wolfram]], and was released to the public on May 15, 2009.<ref name="launch date">{{cite web|url=httphttps://blog.wolframalpha.com/2009/05/08/so-much-for-a-quiet-launch/ |title=So Much for A Quiet Launch |publisher=Wolfram Alpha Blog |date=2009-05-08 |access-date=2009-10-20}}</ref>

===Siri===

Line 74 ⟶ 78:

===Others===

* [[Ask.com]] – The original idea behind Ask Jeeves (Ask.com) was traditional keyword searching with an ability to get answers to questions posed in everyday, natural language. The current Ask.com still supports this, with added support for math, dictionary, and conversion questions.

* [[Braina]]<ref>{{cite web|url=httphttps://www.brainasoft.com/braina/|title=Braina - Artificial Intelligence Software for Windows|website=www.brainasoft.com|access-date=29 January 2018}}</ref> – Braina is a natural language interface for [[Windows OS]] that allows to type or speak English language sentences to perform a certain action or find information.

[[File:GNOME Do Classic.png|thumb|Screenshot of GNOME DO classic interface.]]

* [[GNOME Do]] – Allows for quick finding miscellaneous artifacts of GNOME environment (applications, Evolution and Pidgin contacts, Firefox bookmarks, Rhythmbox artists and albums, and so on) and execute the basic actions on them (launch, open, email, chat, play, etc.).<ref>Ubuntu 10.04 Add/Remove Applications description for GNOME Do</ref>

* [[hakia]] – hakia was an Internet search engine. The company invented an alternative new infrastructure to indexing that used SemanticRank algorithm, a solution mix from the disciplines of ontological semantics, fuzzy logic, computational linguistics, and mathematics. hakia closed in 2014.

Line 101 ⟶ 105:

{{Internet search}}

{{Computable knowledge}}

{{Natural Language Processing}}

{{DEFAULTSORT:Natural language user interface}}

[[Category:User interfaces]]

[[Category:Artificial intelligence applications]]

[[Category:Natural language processing]]

[[Category:Computational linguistics]]