Editing Autocomplete (section)

== Definition ==
=== Original purpose ===
The original purpose of word prediction software was to help people with [[physical disabilities]] increase their typing speed,<ref name=tam2009>{{Cite journal |doi = 10.1080/10400430903175473|pmid = 19908678|title = Evaluating the Benefits of Displaying Word Prediction Lists on a Personal Digital Assistant at the Keyboard Level|journal = Assistive Technology|volume = 21|issue = 3|pages = 105–114|year = 2009|last1 = Tam|first1 = Cynthia|last2 = Wells|first2 = David|s2cid = 23183632}}</ref> as well as to help them decrease the number of keystrokes needed in order to complete a word or a sentence.<ref name =anson>{{cite journal |last1=Anson |first1=D. |last2=Moist |first2=P. |last3=Przywara |first3=M. |last4=Wells |first4=H. |last5=Saylor |first5=H. |last6=Maxime |first6=H. |title=The Effects of Word Completion and Word Prediction on Typing Rates Using On-Screen Keyboards |journal=Assistive Technology |volume=18 |issue=2 |pages=146–154 |date=2006 |doi=10.1080/10400435.2006.10131913  |url=https://www.researchgate.net/publication/6567291 |pmid=17236473|s2cid=11193172 }}</ref> The need to increase speed is noted by the fact that people who use [[speech-generating device]]s generally produce speech at a rate that is less than 10% as fast as people who use oral speech.<ref name =trnka>{{cite book |last1=Trnka |first1=K. |last2=Yarrington |first2=J.M. |last3=McCoy |first3=K.F. |chapter=The Effects of Word Prediction on Communication Rate for AAC |chapter-url= |editor= |title=NAACL-Short '07: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics |publisher=Association for Computational Linguistics |volume=Companion Volume, Short Papers |date=2007 |citeseerx=10.1.1.363.2416 |pages=173–6 |url=}}</ref> But the function is also very useful for anybody who writes text, particularly people–such as medical doctors–who frequently use long, hard-to-spell terminology that may be technical or medical in nature.

=== Description ===
Autocomplete or word completion works so that when the writer writes the first letter or letters of a word, the program predicts one or more possible words as choices. If the intended word is included in the list, the writer can select it, for example, by using the number keys. If the word that the user wants is not predicted, the writer must enter the next letter of the word. At this time, the word choice(s) is altered so that the words provided begin with the same letters as those that have been selected. When the word that the user wants appears it is selected, and the word is inserted into the text.<ref name=b77>{{cite book |last1=Beukelman |first1=D.R. |last2=Mirenda |first2=P. |title=Augmentative and Alternative Communication: Supporting Children and Adults with Complex Communication Needs |publisher=Brookes |location=Baltimore, MD |date=2005 |isbn=9781557666840 |pages=77 |edition=3rd |oclc=254228982}}</ref><ref name="witten">{{cite book |last1=Witten |first1=I.H. |last2=Darragh |first2=John J. |title=The reactive keyboard |publisher=Cambridge University Press |year=1992 |pages=43–44 |isbn=978-0-521-40375-7 |url=https://books.google.com/books?id=obxCY0wcaTgC&pg=PA44}}</ref> In another form of word prediction, words most likely to follow the just written one are predicted, based on recent word pairs used.<ref name="witten"/>  Word prediction uses [[language modeling]], where within a set vocabulary the words are most likely to occur are calculated.<ref>{{cite book |first=F. |last=Jelinek |chapter=Self-Organized Language Modeling for Speech Recognition |chapter-url={{GBurl|iDHgboYRzmgC|p=450}} |editor1-last=Waibel |editor1-first=A. |editor2-first=Kai-Fu |editor2-last=Lee |title=Readings in Speech Recognition |publisher=Morgan Kaufmann |date=1990 |isbn=9781558601246 |pages=450 |url=}}</ref>  Along with language modeling, basic word prediction on [[Augmentative and alternative communication|AAC]] devices is often coupled with a [[frecency]] model, where words the AAC user has used recently and frequently are more likely to be predicted.<ref name =trnka/>  Word prediction software often also allows the user to enter their own words into the word prediction dictionaries either directly, or by "learning" words that have been written.<ref name=b77/><ref name="witten"/> Some search returns related to genitals or other vulgar terms are often omitted from autocompletion technologies, as are morbid terms<ref>{{cite journal |first=Jan |last=Oster |title=Communication, defamation and liability of intermediaries |journal=Legal Studies |volume=35 |issue=2 |pages=348–368 |date=2015 |doi=10.1111/lest.12064 |s2cid=143005665 |url=}}</ref><ref>{{cite magazine |last1=McCulloch |first1=Gretchen |title=Autocomplete Presents the Best Version of You |url=https://www.wired.com/story/autocomplete-presents-the-best-version-of-you |access-date=11 February 2019 |magazine=[[Wired (magazine)|Wired]] |date=11 February 2019}}</ref>