Predictive text

From Wikipedia, the free encyclopedia

Jump to: navigation, search

Predictive text is an input technology most commonly used on mobile phones, and for accessibility. The technology allows some common words to be entered by a single keypress for each letter, as opposed to the multiple keypress approach used in the older generation of mobile phones. The intent is to simplify the writing of text messages, e-mail, entries into an address book or calendar, and the like. Theoretically, the number of keystrokes per character, on average, is comparable to using a Qwerty keyboard, provided that all words used (including all slang, proper nouns, abbreviations, urls, foreign-language words and so on) are in the dictionary (for dictionary-based methods), that no spelling mistakes or typing mistakes are made, and that punctuation is ignored [1]. In experiments with real users, it is found that these factors cannot be ignored, and are rather critical to speed and accuracy. [2]


Contents

[edit] Background

Short message service (SMS) permits a mobile phone user to send text messages, (also called messages, SMSes, texts, and txts) as a short message. The most common system of SMS text input is referred to as "multi-tap". Using multi-tap, a key is pressed multiple times to access the list of letters on that key. For instance, pressing the"2" key once displays an, "a", twice displays a "b" and three times displays a "c". To enter two successive letters that are on the same key, the user must either pause or hit a "next" button. A user can type by pressing an alphanumeric keypad without looking at the electronic equipment display. Thus, multi-tap is easy to understand, and can be used without any visual feedback. However, multi-tap is not very efficient and is considered a hindrance by many users of electronic equipment. Also, since all twenty-six letters of the English language are entered using only eight alphanumeric keys, it is difficult to use SMS.

Predictive text entry software generally reduces the number of key strokes a user is required to enter a word, given the limitations expressed above (no typing or spelling errors, etc.), the user presses the number corresponding to each letter and, as long as the word exists in the predictive text dictionary, for dictionary-based methods, or correctly disambiguated by non-dictionary systems, it will appear. For instance, pressing "4663" will typically be disambiguated as the word "good", provided that a linguistic database in English is currently in use. The most widely used systems of predictive text dictionaries are T9 and iTap. The competing Eatoni products do not use a dictionary. Each of these systems requires the manufacturer to install a linguistic database for every input language to be supported.

[edit] Dictionary vs. non-dictionary systems

Traditional disambiguation works by referencing a dictionary of commonly used words, though Eatoni offers a dictionary-less disambiguation system. In dictionary-based systems, as the user presses the number buttons, an algorithm searches the dictionary for a list of possible words that match the keypress combination, and offers up the most probable choice. The user can then confirm the selection and move on, or use a key to cycle through the possible combinations. A non-dictionary system constructs words and other sequences of letters from the statistics of word parts.

To attempt predictions of the intended result of keystrokes not yet entered, disambiguation may be combined with a word completion facility.

A disambiguation or predictive system may include a user database for storing entered words or phrases which are not well-disambiguated by the pre-supplied database. When words are entered into the user database without direct user intervention, such systems are sometimes referred to as "learning" systems. Some disambiguation systems further attempt to correct spelling, format text or perform other automatic rewrites, with the effect of either enhancing or frustrating user efforts to enter text.

[edit] History

Predictive entry of text from a telephone keypad has been known at least since the 1970s (Smith and Goodwin, 1971). Aspects of predictive text have been patented for instance by Kondraske(1985), and as a fully functional keypad to text system for communicating with deaf people via phone in 1988 (Roy Feinson #4,754,474) . Predictive text was mainly used to look up names in directories over the phone, until mobile phone text messaging came into widespread use.

[edit] Example

Consider a typical phone keypad:

A standard ITU-T E.161 keypad used for text messaging

Suppose a user wishes to type "The". In a traditional "multi-tap" keypad entry system, it would be necessary to do the following:

  • Press 8 (tuv) once to select t.
  • Press 4 (ghi) twice to select h.
  • Press 3 (def) twice to select e.

Meanwhile, in a phone with predictive text, it is only necessary to:

  • Press 8 once to select the (tuv) group for the first character.
  • Press 4 once to select the (ghi) group for the second character.
  • Press 3 once to select the (def) group for the third character.

The system updates the display as each keypress is entered to show the most probable entry. In this case, predictive text reduced the number of button presses from 5 to 3. The effect is even greater with longer, more complex words.

A dictionary-based predictive system is based on hope that the desired word is in the dictionary. That hope may be misplaced if the word differs in any way from common usage—in particular, if the word is not spelled or typed correctly, is slang, or is a proper noun. In these cases, some other mechanism must be used to enter the word.

Furthermore, the simple dictionary approach fails with agglutinative languages, where a single word doesn't necessarily represent a single semantic entity.

[edit] Companies and products

Predictive text is developed and marketed in a variety of competing products. Nuance Communications's T9 is the market leader. Other products include Motorola's iTap, Eatoni Ergonomic's LetterWise, (character, rather than word-based prediction), WordWise (word-based prediction without a dictionary), EQ3 (a Qwerty-like layout compatible with regular telephone keypads); Prevalent Devices's Phraze-It; Xrgomics' TenGO (a six-key reduced QWERTY keyboard system); Adaptxt (considers language, context, grammar and semantics); CleverTexting (statistical nature of the language, dictionary less, dynamic key allocation) ; and Oizea Type (temporal ambiguity).

[edit] Textonyms

As mentioned above, the key sequence 4663 on a telephone keypad, provided with a linguistic database in English, will generally be disambiguated as the word "good". However, the same key sequence also corresponds to other words, such as "home", "gone", "hoof", "hood" and so on. Such confusions may lead to mistaken meaning even if all of the words are typed correctly and spelled correctly. For example, "Are you home in bed?" could be rendered as "Are you good in bed?"

Words produced by the same combination of keypresses are technically paragrams,[1] but colloquially they're often referred to as "isotaps", "textonyms" (or "txtonyms",) "adaptonyms", "cellodromes", or "T9onyms" (pronounced "tynonyms").[2]

One quoted example of textonyms shows that the keypresses required to produce the message "Ask the cool barmaid for nine pints of beer" could result in "Ask tie book carnage for mind shots me adds". Such examples illustrate the importance of proof-reading text messages after typing them, or developing disambiguation systems with lower ambiguity.

Some "textonyms" include

  • 63 = me, of
  • 5477 = kiss, lips, lisp

According to the ispell dictionaries, other examples of textonyms are:

  • 22737 = acres bards barer bares barfs baser bases bbses caper capes cards carer cares cases (English; 14 words)
  • 7254 = σάκη σακί ράλι πάλη ρακί σάμι ρακή ραμί ράκη σάλι σάμη σαλή πάλι (Greek; 13 words)

Such textonyms may even be adopted in regular speech, particularly by teenagers; for example, the use of "book" to mean "cool",[3], "idiom" to mean "Heino" (an abbreviation for "Heineken", used in Dublin) and "Zonino!" used to mean "Woohoo!".[citation needed]

[edit] Missing words and misspelling

Textonyms are not the only issues limiting the effectiveness of predictive text implementations. For some implementations, there may be a large number of gibberish words such as Blairf, which appears with the input 252473. The other default suggestion for this combination of key presses is Blaire (a reasonably common surname). It has been observed that phones that contain the word blairf, such as the Sony Ericsson K610i, do not by default contain the name Claire.[citation needed]

A misspelling or mistyping may lead to an unintended consequences. For instance, a user may have intended 4663 to mean "home" but mistyped the word as 463 leading to the word "god". In this case the intended sentence "are you home in bed?" would be rendered as "are you god in bed?". For dictionary-based systems, a mistyping or misspelling may not be in the dictionary at all, typically resulting in gibberish.

[edit] See also

[edit] Concepts

[edit] Products

  • T9 (predictive text)
  • ITap
  • LetterWise
  • Q9 input method – method for inputting Chinese characters on a standard mobile phone keyboard
  • CleverTexting - Statistical predictive texting
  • Panini Keypad - Texting technology for 11 regional languages of India.

[edit] Devices

[edit] Notes

  1. ^  Paragram - a word formed by altering a letter or group of letters in another word.[citation needed]

[edit] External links

[edit] References

  1. ^ I. Scott MacKenzie (2002). "KSPC (Keystrokes per Character) as a Characteristic of Text Entry Techniques". Proceedings of MobileHCI 2002. http://www.yorku.ca/mack/hcimobile02.PDF. 
  2. ^ O'Riordan et. al. "Investigating Text Input Methods for Mobile Phones". J. Computer Sci, I (2):189-199, 2005. http://www.scipub.org/fulltext/jcs/jcs12189-199.pdf.. 

[edit] Companies

[edit] Additional reference

Retrieved from "http://en.wikipedia.org/wiki/Predictive_text"
Personal tools