257:". 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, requiring potentially many keystrokes to enter a single letter.
273:, foreign-language words and other user-unique words. This ideal circumstance gives predictive text software the reduction in the number of key strokes a user is required to enter a word. The user presses the number corresponding to each letter and, as long as the word exists in the predictive text dictionary, or is correctly disambiguated by non-dictionary systems, it will appear. For instance, pressing "4663" will typically be interpreted as the word
374:
39:
587:), though they are not specific to T9. Selecting the wrong textonym can occur with no misspelling or typo, if the wrong textonym is selected by default or user error. 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
364:
The actuating keys of the
Chinese typewriter created by Lin Yutang in the 1940s included suggestions for the characters following the one selected. In 1951, the Chinese typesetter Zhang Jiying arranged Chinese characters in associative clusters, a precursor of modern predictive text entry, and broke
233:
systems, because the predicted text that is automatically written that provide the speed and mechanical efficiency benefit, could, if the user is not careful to review, result in transmitting misinformation. Predictive text systems take time to learn to use well, and so generally, a device's system
757:
Values for
English range from about 10 for methods using only cursor keys and a SELECT key to about 0.5 for word prediction techniques. It is demonstrated that KSPC is useful for a priori analyses, thereby supporting the characterisation and comparison of text-entry methods before labour-intensive
328:
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
340:
Either system (disambiguation or predictive) may include a user database, which can be further classified as a "learning" system when words or phrases are entered into the user database without direct user intervention. The user database is for storing words or phrases which are not well
365:
speed records by doing so. Predictive entry of text from a telephone keypad has been known at least since the 1970s (Smith and
Goodwin, 1971). Predictive text was mainly used to look up names in directories over the phone, until mobile phone text messaging came into widespread use.
456:
The system updates the display as each keypress is entered, to show the most probable entry. In this example, prediction reduced the number of button presses from five to three. The effect is even greater with longer words and those composed of letters later in each key's sequence.
308:
and WordWise. T9 and iTap use dictionaries, but Eatoni
Ergonomics' products uses a disambiguation process, a set of statistical rules to recreate words from keystroke sequences. All predictive text systems require a linguistic database for every supported input language.
218:. This is approximately true providing that all words used are in its database, punctuation is ignored, and no input mistakes are made typing or spelling. The theoretical keystrokes per character, KSPC, of a keyboard is KSPC=1.00, and of multi-tap is KSPC=2.03. Eatoni's
460:
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
666:
Textonyms are not the only issue limiting the effectiveness of predictive text implementations. Another significant problem are words for which the disambiguation produces a single, incorrect response. The system may, for example, respond with
341:
disambiguated by the pre-supplied database. Some disambiguation systems further attempt to correct spelling, format text or perform other automatic rewrites, with the risky effect of either enhancing or frustrating user efforts to enter text.
607:
and so on. For example, "Are you home?" could be rendered as "Are you good?" if the user neglects to alter the default 4663 word. This can lead to misunderstandings; for example sequence 735328 might correspond to either
332:
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
201:/WordWise. There are many ways to build a device that predicts text, but all predictive text systems have initial linguistic settings that offer predictions that are re-prioritized to adapt to each user. This
537:(temporal ambiguity); Intelab's Tauto; WordLogic's Intelligent Input Platform™ (patented, layer-based advanced text prediction, includes multi-language dictionary, spell-check, built-in Web search); Google's
260:
In ideal predictive text entry, all words used are in the dictionary, punctuation is ignored, no spelling mistakes are made, and no typing mistakes are made. The ideal dictionary would include all slang,
211:
feedback that results in corrective key presses, such as pressing a "next" key to get to the intention. Most predictive text systems have a user database to facilitate this process.
19:
This article is about word completion on limited physical keyboards, such as early mobile phone keyboards. For a similar article for general keyboards, smartphones and tablets, see
229:, the user's level of learned ability to operate predictive text software, and the user's efficiency goal. There are various levels of risk in predictive text systems, versus
925:
683:
or misspellings occur, they are very unlikely to be recognized correctly by a disambiguation system, though error correction mechanisms may mitigate that effect.
158:
rather than repeatedly sequencing through the same group of "letters" it represents, in the same, invariable order. Predictive text could allow for an entire
1059:
1219:
506:
494:
826:
530:
1197:
534:
623:
was sparked by a textonym error. Predictive text choosing a default different from that which the user expects has similarities with the
510:
549:
Words produced by the same combination of keypresses have been called "textonyms"; also "txtonyms"; or "T9onyms" (pronounced "tynonyms"
514:
1608:
1052:
956:
214:
Theoretically the number of keystrokes required per desired character in the finished writing is, on average, comparable to using a
353:
technology was invented out of necessities by
Chinese scientists and linguists in the 1950s to solve the input inefficiency of the
322:
1777:
518:
253:(also called messages, SMSes, texts, and txts) as a short message. The most common system of SMS text input is referred to as "
465:. In these cases, some other mechanism must be used to enter the word. Furthermore, the simple dictionary approach fails with
679:, both of which correspond to the keystroke sequence, but are not, in this example, found by the predictive text system. When
103:
933:
75:
1818:
1518:
1209:
1045:
1772:
1379:
82:
222:
is a predictive multi-tap hybrid, which when operating on a standard telephone keypad achieves KSPC=1.15 for
English.
1533:
1364:
878:
122:
1304:
56:
1721:
1374:
89:
234:
has user options to set up the choice of multi-tap or of any one of several schools of predictive text methods.
1369:
1114:
60:
501:(character, rather than word-based prediction); WordWise (word-based prediction without a dictionary); EQ3 (a
1638:
1359:
906:. University College London: Centre for Mathematics and Physics in the Life Sciences and Experimental Biology
27:
71:
1331:
1676:
1661:
1633:
1498:
1493:
1068:
1027:
1813:
1413:
1384:
1162:
987:
Smith, Sidney L.; Goodwin, Nancy C. (1971). "Alphabetic Data Entry Via the Touch-Tone Pad: A Comment".
771:
1256:
1109:
1782:
1706:
1438:
1394:
1279:
1177:
162:
to be input by single keypress. Predictive text makes efficient use of fewer device keys to input
277:, provided that a linguistic database in English is currently in use, though alternatives such as
1686:
1656:
1323:
845:
727:
49:
1157:
807:
1543:
1236:
1214:
1204:
1172:
1147:
466:
1808:
1403:
478:
242:
96:
1022:
900:
1756:
1432:
1408:
1261:
786:
707:
697:
482:
293:
225:
The choice of which predictive text system is the best to use involves matching the user's
215:
186:
8:
1736:
1666:
1623:
1579:
1351:
1341:
1336:
1224:
1032:
961:
712:
262:
194:
1746:
1618:
1483:
1246:
1229:
1087:
1004:
879:"Slang early-warning alert: 'Book' is the new 'cat's pajamas' | Change of Subject"
358:
354:
477:
Predictive text is developed and marketed in a variety of competing products, such as
1751:
1463:
1271:
1182:
301:
1008:
1628:
1513:
1488:
1289:
1192:
996:
791:
624:
552:
533:(statistical nature of the language, dictionaryless, dynamic key allocation); and
203:
143:
139:
650:
was the default in predictive text systems that assumed it was more frequent than
1740:
1696:
1564:
1294:
1167:
1142:
1124:
334:
1448:
1428:
1152:
1000:
717:
469:, where a single word does not necessarily represent a single semantic entity.
1037:
749:"KSPC (Keystrokes per Character) as a Characteristic of Text Entry Techniques"
226:
142:
used where one key or button represents many letters, such as on the physical
1802:
1711:
1523:
1503:
1284:
628:
266:
250:
151:
748:
1691:
1309:
722:
702:
620:
350:
246:
175:
147:
20:
591:. However, the same key sequence also corresponds to other words, such as
1648:
1528:
1241:
1134:
1082:
635:
462:
1251:
655:
498:
318:
305:
219:
198:
26:"Predictive search" redirects here. For the search engine feature, see
1119:
254:
230:
357:, as the typing process involved finding and selecting thousands of
38:
1594:
1574:
1559:
1538:
1508:
1453:
1418:
1299:
486:
373:
179:
1731:
1589:
1569:
1443:
1187:
1102:
772:"Chinese typewriter anticipated predictive text, finds historian"
613:
522:
163:
1097:
1092:
538:
502:
361:
on a tray, drastically slowing down the word processing speed.
289:
are also valid interpretations of the sequence of key strokes.
171:
1787:
1423:
381:
378:
827:"How This Decades-Old Technology Ushered In Predictive Text"
430:
Meanwhile, in a phone with predictive text, they need only:
292:
The most widely used systems of predictive text are Tegic's
680:
567:
561:
490:
297:
270:
190:
185:
The most widely used, general, predictive text systems are
526:
392:
in a "multi-tap" keypad entry system, they would need to:
1584:
661:
573:
505:-like layout compatible with regular telephone keypads);
167:
445:
once to select the (ghi) group for the second character.
312:
808:"Why predictive text is making you forget how to write"
452:
once to select the (def) group for the third character.
438:
once to select the (tuv) group for the first character.
1033:
Technical notes on iTap (including lists of textonyms)
525:(considers language, context, grammar and semantics);
579:
570:
564:
558:
576:
555:
388:On a typical phone keypad, if users wished to type
63:. Unsourced material may be challenged and removed.
746:
631:changes a spelling to that of an unintended word.
317:Traditional disambiguation works by referencing a
671:upon input of 252473, when the intended word was
207:adapts, by way of the device memory, to a user's
1800:
1270:
1067:
957:"Predictive text creating secret teen language"
325:offers a dictionaryless disambiguation system.
1053:
824:
1028:An Australian newspaper article on textonyms
986:
926:"Indefinite sentence for killing his friend"
529:(a predictive typing software for Windows);
521:(a six-key reduced QWERTY keyboard system);
154:technologies. Each key press results in a
1060:
1046:
806:Greenwood, Veronique (14 December 2016).
805:
778:
472:
123:Learn how and when to remove this message
16:Input technology for mobile phone keypads
638:slang; for example, the use of the word
372:
954:
873:
871:
769:
1801:
881:. Blogs.chicagotribune.com. 2007-01-19
843:
825:O'Donovan, Caroline (16 August 2016).
787:"How it Works: The Chinese Typewriter"
784:
662:Disambiguation failure and misspelling
1041:
785:Sorrel, Charlie (February 23, 2009).
313:Dictionary vs. non-dictionary systems
1519:Simple Knowledge Organization System
898:
868:
61:adding citations to reliable sources
32:
13:
1023:New Scientist article on textonyms
980:
14:
1830:
1534:Thesaurus (information retrieval)
1016:
770:Mcclure, Max (12 November 2012).
551:
37:
955:Alleyne, Richard (5 Feb 2008).
948:
758:implementations and evaluations
321:of commonly used words, though
48:needs additional citations for
1115:Natural language understanding
932:. 2 April 2011. Archived from
918:
892:
844:Fisher, Jamie (8 March 2018).
837:
818:
799:
763:
740:
384:keypad used for text messaging
1:
1639:Optical character recognition
753:Proceedings of MobileHCI 2002
733:
237:
28:search suggest drop-down list
1332:Multi-document summarization
619:. A 2010 brawl that led to
544:
7:
1819:Natural language processing
1662:Latent Dirichlet allocation
1634:Natural language generation
1499:Machine-readable dictionary
1494:Linguistic Linked Open Data
1069:Natural language processing
747:I. Scott MacKenzie (2002).
691:
686:
10:
1835:
1414:Explicit semantic analysis
1163:Deep linguistic processing
1001:10.1177/001872087101300212
368:
344:
25:
18:
1765:
1720:
1675:
1647:
1607:
1552:
1474:
1462:
1393:
1350:
1322:
1257:Word-sense disambiguation
1133:
1110:Computational linguistics
1075:
485:. Other products include
227:preferred interface style
1783:Natural Language Toolkit
1707:Pronunciation assessment
1609:Automatic identification
1439:Latent semantic analysis
1395:Distributional semantics
1280:Compound-term processing
1178:Named-entity recognition
349:The predictive text and
1687:Automated essay scoring
1657:Document classification
1324:Automatic summarization
728:Speech-to-text reporter
634:Textonyms were used as
467:agglutinative languages
329:possible combinations.
1544:Universal Dependencies
1237:Terminology extraction
1220:Semantic decomposition
1215:Semantic role labeling
1205:Part-of-speech tagging
1173:Information extraction
1158:Coreference resolution
1148:Collocation extraction
850:London Review of Books
473:Companies and products
385:
359:logographic characters
1305:Sentence segmentation
846:"The Left-Handed Kid"
654:. This is related to
479:Nuance Communications
376:
243:Short message service
1757:Voice user interface
1468:datasets and corpora
1409:Document-term matrix
1262:Word-sense induction
708:Text entry interface
698:Assistive technology
629:spell-check software
57:improve this article
1737:Interactive fiction
1667:Pachinko allocation
1624:Speech segmentation
1580:Google Ngram Viewer
1352:Machine translation
1342:Text simplification
1337:Sentence extraction
1225:Semantic similarity
962:The Daily Telegraph
713:Input method editor
1747:Question answering
1619:Speech recognition
1484:Corpus linguistics
1464:Language resources
1247:Textual entailment
1230:Sentiment analysis
930:This Is Lancashire
386:
355:Chinese typewriter
1814:Mobile technology
1796:
1795:
1752:Virtual assistant
1677:Computer-assisted
1603:
1602:
1360:Computer-assisted
1318:
1317:
1310:Word segmentation
1272:Text segmentation
1210:Semantic analysis
1198:Syntactic parsing
1183:Ontology learning
899:Dartmelk, Jewis.
507:Prevalent Devices
302:Eatoni Ergonomics
133:
132:
125:
107:
72:"Predictive text"
1826:
1773:Formal semantics
1722:Natural language
1629:Speech synthesis
1611:and data capture
1514:Semantic network
1489:Lexical resource
1472:
1471:
1290:Lexical analysis
1268:
1267:
1193:Semantic parsing
1062:
1055:
1048:
1039:
1038:
1012:
974:
973:
971:
969:
952:
946:
945:
943:
941:
922:
916:
915:
913:
911:
905:
896:
890:
889:
887:
886:
875:
866:
865:
863:
861:
841:
835:
834:
822:
816:
815:
803:
797:
796:
782:
776:
775:
767:
761:
760:
744:
625:Cupertino effect
586:
585:
582:
581:
578:
575:
572:
569:
566:
563:
560:
557:
495:Eatoni Ergonomic
422:twice to select
411:twice to select
245:(SMS) permits a
182:, and the like.
140:input technology
128:
121:
117:
114:
108:
106:
65:
41:
33:
1834:
1833:
1829:
1828:
1827:
1825:
1824:
1823:
1799:
1798:
1797:
1792:
1761:
1741:Syntax guessing
1723:
1716:
1702:Predictive text
1697:Grammar checker
1678:
1671:
1643:
1610:
1599:
1565:Bank of English
1548:
1476:
1467:
1458:
1389:
1346:
1314:
1266:
1168:Distant reading
1143:Argument mining
1129:
1125:Text processing
1071:
1066:
1019:
983:
981:Further reading
978:
977:
967:
965:
953:
949:
939:
937:
936:on 4 March 2016
924:
923:
919:
909:
907:
903:
897:
893:
884:
882:
877:
876:
869:
859:
857:
842:
838:
823:
819:
804:
800:
783:
779:
768:
764:
745:
741:
736:
694:
689:
664:
554:
550:
547:
475:
400:once to select
371:
347:
335:word completion
315:
240:
144:numeric keypads
136:Predictive text
129:
118:
112:
109:
66:
64:
54:
42:
31:
24:
17:
12:
11:
5:
1832:
1822:
1821:
1816:
1811:
1794:
1793:
1791:
1790:
1785:
1780:
1775:
1769:
1767:
1763:
1762:
1760:
1759:
1754:
1749:
1744:
1734:
1728:
1726:
1724:user interface
1718:
1717:
1715:
1714:
1709:
1704:
1699:
1694:
1689:
1683:
1681:
1673:
1672:
1670:
1669:
1664:
1659:
1653:
1651:
1645:
1644:
1642:
1641:
1636:
1631:
1626:
1621:
1615:
1613:
1605:
1604:
1601:
1600:
1598:
1597:
1592:
1587:
1582:
1577:
1572:
1567:
1562:
1556:
1554:
1550:
1549:
1547:
1546:
1541:
1536:
1531:
1526:
1521:
1516:
1511:
1506:
1501:
1496:
1491:
1486:
1480:
1478:
1469:
1460:
1459:
1457:
1456:
1451:
1449:Word embedding
1446:
1441:
1436:
1429:Language model
1426:
1421:
1416:
1411:
1406:
1400:
1398:
1391:
1390:
1388:
1387:
1382:
1380:Transfer-based
1377:
1372:
1367:
1362:
1356:
1354:
1348:
1347:
1345:
1344:
1339:
1334:
1328:
1326:
1320:
1319:
1316:
1315:
1313:
1312:
1307:
1302:
1297:
1292:
1287:
1282:
1276:
1274:
1265:
1264:
1259:
1254:
1249:
1244:
1239:
1233:
1232:
1227:
1222:
1217:
1212:
1207:
1202:
1201:
1200:
1195:
1185:
1180:
1175:
1170:
1165:
1160:
1155:
1153:Concept mining
1150:
1145:
1139:
1137:
1131:
1130:
1128:
1127:
1122:
1117:
1112:
1107:
1106:
1105:
1100:
1090:
1085:
1079:
1077:
1073:
1072:
1065:
1064:
1057:
1050:
1042:
1036:
1035:
1030:
1025:
1018:
1017:External links
1015:
1014:
1013:
995:(2): 189–190.
982:
979:
976:
975:
947:
917:
891:
867:
836:
817:
798:
777:
762:
738:
737:
735:
732:
731:
730:
725:
720:
718:Text messaging
715:
710:
705:
700:
693:
690:
688:
685:
663:
660:
546:
543:
474:
471:
454:
453:
446:
439:
428:
427:
416:
405:
370:
367:
346:
343:
314:
311:
239:
236:
209:disambiguating
131:
130:
45:
43:
36:
15:
9:
6:
4:
3:
2:
1831:
1820:
1817:
1815:
1812:
1810:
1807:
1806:
1804:
1789:
1786:
1784:
1781:
1779:
1778:Hallucination
1776:
1774:
1771:
1770:
1768:
1764:
1758:
1755:
1753:
1750:
1748:
1745:
1742:
1738:
1735:
1733:
1730:
1729:
1727:
1725:
1719:
1713:
1712:Spell checker
1710:
1708:
1705:
1703:
1700:
1698:
1695:
1693:
1690:
1688:
1685:
1684:
1682:
1680:
1674:
1668:
1665:
1663:
1660:
1658:
1655:
1654:
1652:
1650:
1646:
1640:
1637:
1635:
1632:
1630:
1627:
1625:
1622:
1620:
1617:
1616:
1614:
1612:
1606:
1596:
1593:
1591:
1588:
1586:
1583:
1581:
1578:
1576:
1573:
1571:
1568:
1566:
1563:
1561:
1558:
1557:
1555:
1551:
1545:
1542:
1540:
1537:
1535:
1532:
1530:
1527:
1525:
1524:Speech corpus
1522:
1520:
1517:
1515:
1512:
1510:
1507:
1505:
1504:Parallel text
1502:
1500:
1497:
1495:
1492:
1490:
1487:
1485:
1482:
1481:
1479:
1473:
1470:
1465:
1461:
1455:
1452:
1450:
1447:
1445:
1442:
1440:
1437:
1434:
1430:
1427:
1425:
1422:
1420:
1417:
1415:
1412:
1410:
1407:
1405:
1402:
1401:
1399:
1396:
1392:
1386:
1383:
1381:
1378:
1376:
1373:
1371:
1368:
1366:
1365:Example-based
1363:
1361:
1358:
1357:
1355:
1353:
1349:
1343:
1340:
1338:
1335:
1333:
1330:
1329:
1327:
1325:
1321:
1311:
1308:
1306:
1303:
1301:
1298:
1296:
1295:Text chunking
1293:
1291:
1288:
1286:
1285:Lemmatisation
1283:
1281:
1278:
1277:
1275:
1273:
1269:
1263:
1260:
1258:
1255:
1253:
1250:
1248:
1245:
1243:
1240:
1238:
1235:
1234:
1231:
1228:
1226:
1223:
1221:
1218:
1216:
1213:
1211:
1208:
1206:
1203:
1199:
1196:
1194:
1191:
1190:
1189:
1186:
1184:
1181:
1179:
1176:
1174:
1171:
1169:
1166:
1164:
1161:
1159:
1156:
1154:
1151:
1149:
1146:
1144:
1141:
1140:
1138:
1136:
1135:Text analysis
1132:
1126:
1123:
1121:
1118:
1116:
1113:
1111:
1108:
1104:
1101:
1099:
1096:
1095:
1094:
1091:
1089:
1086:
1084:
1081:
1080:
1078:
1076:General terms
1074:
1070:
1063:
1058:
1056:
1051:
1049:
1044:
1043:
1040:
1034:
1031:
1029:
1026:
1024:
1021:
1020:
1010:
1006:
1002:
998:
994:
990:
989:Human Factors
985:
984:
964:
963:
958:
951:
935:
931:
927:
921:
902:
895:
880:
874:
872:
855:
851:
847:
840:
832:
828:
821:
813:
812:New Scientist
809:
802:
794:
793:
788:
781:
773:
766:
759:
754:
750:
743:
739:
729:
726:
724:
721:
719:
716:
714:
711:
709:
706:
704:
701:
699:
696:
695:
684:
682:
678:
674:
670:
659:
657:
653:
649:
645:
641:
637:
632:
630:
626:
622:
618:
615:
611:
606:
602:
598:
594:
590:
584:
542:
540:
536:
532:
531:Clevertexting
528:
524:
520:
516:
512:
508:
504:
500:
496:
492:
488:
484:
480:
470:
468:
464:
458:
451:
447:
444:
440:
437:
433:
432:
431:
425:
421:
417:
414:
410:
406:
403:
399:
395:
394:
393:
391:
383:
380:
375:
366:
362:
360:
356:
352:
342:
338:
336:
330:
326:
324:
320:
310:
307:
303:
299:
296:, Motorola's
295:
290:
288:
284:
280:
276:
272:
268:
267:abbreviations
264:
258:
256:
252:
251:text messages
249:user to send
248:
244:
235:
232:
228:
223:
221:
217:
212:
210:
206:
205:
200:
196:
192:
188:
183:
181:
177:
173:
169:
165:
161:
157:
153:
152:accessibility
149:
148:mobile phones
145:
141:
137:
127:
124:
116:
105:
102:
98:
95:
91:
88:
84:
81:
77:
74: –
73:
69:
68:Find sources:
62:
58:
52:
51:
46:This article
44:
40:
35:
34:
29:
22:
1809:Input/output
1701:
1692:Concordancer
1088:Bag-of-words
992:
988:
966:. Retrieved
960:
950:
938:. Retrieved
934:the original
929:
920:
908:. Retrieved
894:
883:. Retrieved
858:. Retrieved
853:
849:
839:
830:
820:
811:
801:
790:
780:
765:
756:
752:
742:
723:SMS language
703:Autocomplete
676:
672:
668:
665:
651:
647:
643:
639:
633:
621:manslaughter
616:
609:
604:
600:
596:
592:
588:
548:
476:
459:
455:
449:
442:
435:
429:
423:
419:
412:
408:
401:
397:
389:
387:
363:
351:autocomplete
348:
339:
331:
327:
316:
291:
286:
282:
278:
274:
263:proper nouns
259:
247:mobile phone
241:
224:
213:
208:
202:
184:
176:address book
168:text message
159:
155:
135:
134:
119:
110:
100:
93:
86:
79:
67:
55:Please help
50:verification
47:
21:Autocomplete
1649:Topic model
1529:Text corpus
1375:Statistical
1242:Text mining
1083:AI-complete
627:, by which
463:proper noun
377:A standard
1803:Categories
1370:Rule-based
1252:Truecasing
1120:Stop words
901:"Txtonyms"
885:2009-07-08
734:References
656:cacography
636:Millennial
535:Oizea Type
499:LetterWise
337:facility.
319:dictionary
306:LetterWise
300:, and the
238:Background
220:LetterWise
199:LetterWise
156:prediction
113:April 2013
83:newspapers
1679:reviewing
1477:standards
1475:Types and
545:Textonyms
511:Phraze-It
255:multi-tap
231:multi-tap
1595:Wikidata
1575:FrameNet
1560:BabelNet
1539:Treebank
1509:PropBank
1454:Word2vec
1419:fastText
1300:Stemming
1009:61164630
860:16 March
831:Buzzfeed
692:Concepts
687:See also
646:, since
642:to mean
527:Lightkey
515:Xrgomics
487:Motorola
216:keyboard
204:learning
180:calendar
1766:Related
1732:Chatbot
1590:WordNet
1570:DBpedia
1444:Seq2seq
1188:Parsing
1103:Trigram
968:5 April
940:5 April
910:5 April
614:antonym
612:or its
523:Adaptxt
420:3 (def)
409:4 (ghi)
398:8 (tuv)
369:Example
345:History
195:eZiText
166:into a
164:writing
150:and in
97:scholar
1739:(c.f.
1397:models
1385:Neural
1098:Bigram
1093:n-gram
1007:
677:Claire
673:Blaise
669:Blairf
617:reject
610:select
539:Gboard
503:QWERTY
448:Press
441:Press
434:Press
418:Press
407:Press
396:Press
323:Eatoni
197:, and
172:e-mail
138:is an
99:
92:
85:
78:
70:
1788:spaCy
1433:large
1424:GloVe
1005:S2CID
904:(PDF)
792:Wired
681:typos
519:TenGO
382:E.161
379:ITU-T
174:, an
170:, an
104:JSTOR
90:books
1553:Data
1404:BERT
970:2013
942:2013
912:2013
862:2018
652:cool
648:book
644:cool
640:book
605:hood
601:hoof
597:gone
593:home
589:good
491:iTap
298:iTap
287:hoof
285:and
283:hood
279:home
275:good
271:URLs
191:iTap
178:, a
160:word
76:news
1585:UBY
997:doi
856:(5)
675:or
509:'s
497:'s
493:;
489:'s
481:'s
390:the
146:of
59:by
1805::
1003:.
993:13
991:.
959:.
928:.
870:^
854:40
852:.
848:.
829:.
810:.
789:.
755:.
751:.
658:.
603:,
599:,
595:,
562:aɪ
541:.
517:'
513:;
483:T9
304:'
294:T9
281:,
269:,
265:,
193:,
189:,
187:T9
1743:)
1466:,
1435:)
1431:(
1061:e
1054:t
1047:v
1011:.
999::
972:.
944:.
914:.
888:.
864:.
833:.
814:.
795:.
774:.
583:/
580:z
577:m
574:ɪ
571:n
568:ə
565:n
559:t
556:ˈ
553:/
450:3
443:4
436:8
426:.
424:e
415:.
413:h
404:.
402:t
126:)
120:(
115:)
111:(
101:·
94:·
87:·
80:·
53:.
30:.
23:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
