{"id":"https://openalex.org/W2169587990","doi":"https://doi.org/10.1162/coli_r_00180","title":"<b>Natural Language Processing for Historical Texts</b> <b>Michael Piotrowski</b> (Leibniz Institute of European History) Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 17), 2012, ix+157 pp; paperbound, ISBN 978-1608459469","display_name":"<b>Natural Language Processing for Historical Texts</b> <b>Michael Piotrowski</b> (Leibniz Institute of European History) Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 17), 2012, ix+157 pp; paperbound, ISBN 978-1608459469","publication_year":2013,"publication_date":"2013-11-04","ids":{"openalex":"https://openalex.org/W2169587990","doi":"https://doi.org/10.1162/coli_r_00180","mag":"2169587990"},"language":"en","primary_location":{"id":"doi:10.1162/coli_r_00180","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00180","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/231/1812796/coli_r_00180.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"book-review","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/40/1/231/1812796/coli_r_00180.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045392938","display_name":"Laurent Romary","orcid":"https://orcid.org/0000-0002-0756-0508"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I192389796","display_name":"Cal Poly Humboldt","ror":"https://ror.org/02qt0xs84","country_code":"US","type":"education","lineage":["https://openalex.org/I192389796"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Laurent Romary","raw_affiliation_strings":["Inria & Humboldt University, Berlin","Laurent Romary is director of research at Inria, France, and guest scientist at the Humboldt University in Berlin. He has been involved for many years in language resource modeling activities and in particular in standardization initiatives in the TEI consortium and ISO committee TC 37/SC 4 (language resource management). He is the director of the European DARIAH digital infrastructure in the humanities"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & Humboldt University, Berlin","institution_ids":["https://openalex.org/I192389796"]},{"raw_affiliation_string":"Laurent Romary is director of research at Inria, France, and guest scientist at the Humboldt University in Berlin. He has been involved for many years in language resource modeling activities and in particular in standardization initiatives in the TEI consortium and ISO committee TC 37/SC 4 (language resource management). He is the director of the European DARIAH digital infrastructure in the humanities","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045392938"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I192389796"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"231","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8424000144004822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8424000144004822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compendium","display_name":"Compendium","score":0.6398589015007019},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5787118673324585},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4834947884082794},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.45670175552368164},{"id":"https://openalex.org/keywords/history-of-the-book","display_name":"History of the book","score":0.4507293403148651},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.4465852379798889},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.3988426625728607},{"id":"https://openalex.org/keywords/media-studies","display_name":"Media studies","score":0.32624000310897827},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.3068334460258484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.28373315930366516},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27030396461486816},{"id":"https://openalex.org/keywords/classics","display_name":"Classics","score":0.23499247431755066},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21252909302711487},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12561708688735962}],"concepts":[{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.6398589015007019},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5787118673324585},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4834947884082794},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.45670175552368164},{"id":"https://openalex.org/C2778284071","wikidata":"https://www.wikidata.org/wiki/Q998434","display_name":"History of the book","level":2,"score":0.4507293403148651},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.4465852379798889},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3988426625728607},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.32624000310897827},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3068334460258484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28373315930366516},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27030396461486816},{"id":"https://openalex.org/C74916050","wikidata":"https://www.wikidata.org/wiki/Q841090","display_name":"Classics","level":1,"score":0.23499247431755066},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21252909302711487},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12561708688735962},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_r_00180","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00180","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/231/1812796/coli_r_00180.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01016318v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01016318","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, 2014, 40 (1), pp.231-233. &#x27E8;10.1162/COLI_r_00180&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:db8e8a5f742843d9b2cb9235e283bee9","is_oa":false,"landing_page_url":"https://doaj.org/article/db8e8a5f742843d9b2cb9235e283bee9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 40, Iss 1 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_r_00180","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_r_00180","pdf_url":"https://direct.mit.edu/coli/article-pdf/40/1/231/1812796/coli_r_00180.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384167225","https://openalex.org/W2113182373","https://openalex.org/W2119005669","https://openalex.org/W2088998312","https://openalex.org/W4255195499","https://openalex.org/W2481793228","https://openalex.org/W2403214044","https://openalex.org/W2379604225","https://openalex.org/W4205600000","https://openalex.org/W2918622295"],"abstract_inverted_index":{"The":[0,76,508,729,864,1161,1277,1361,1474],"publication":[1,38,1382],"of":[2,10,27,31,56,73,88,96,98,115,122,142,146,159,205,230,246,253,274,306,313,337,345,399,401,409,436,439,451,471,491,505,520,531,534,545,554,559,577,586,605,619,633,657,743,746,770,789,791,799,843,867,874,886,910,976,996,1032,1083,1090,1099,1133,1171,1178,1217,1238,1342,1383,1418,1450,1476,1487,1511,1573],"a":[3,28,54,120,203,210,228,303,442,465,503,516,528,646,666,835,862,974,1066,1079,1150,1233,1280,1366,1377,1387,1407,1415,1463,1497,1509,1517,1597,1602,1635],"scholarly":[4,113,349,1518],"book":[5,77,153,224,248,481,659,712,1410,1464,1651],"is":[6,154,163,198,225,420,448,475,510,581,612,834,921,1069,1122,1163,1232,1256,1265,1392,1426,1465,1620],"always":[7],"the":[8,23,37,52,83,94,125,143,147,150,152,166,170,173,186,234,240,243,247,254,272,291,297,338,342,356,367,407,410,415,437,449,469,476,480,492,556,578,587,589,617,631,634,652,655,699,711,716,719,727,744,760,778,787,797,826,840,844,847,852,868,872,875,882,891,907,946,949,964,997,1006,1028,1071,1075,1088,1097,1100,1106,1110,1130,1146,1172,1176,1186,1218,1239,1247,1253,1273,1288,1297,1325,1340,1395,1409,1412,1424,1445,1459,1467,1484,1491,1505,1524,1538,1546,1550,1558,1567,1574,1582,1593,1606,1613,1624,1650,1653],"conjunction":[9],"an":[11,156,251,263,331,575,740,924,1257,1283,1311,1336,1403,1532,1646],"author's":[12],"desire":[13],"(or":[14],"need)":[15],"to":[16,33,45,51,69,82,112,139,213,218,371,384,392,463,497,501,513,542,726,753,831,915,933,935,958,963,1004,1047,1103,1144,1169,1213,1261,1309,1535,1557,1626,1643],"disseminate":[17],"their":[18,99,1301],"experience":[19,167,208],"and":[20,22,86,182,249,271,283,317,324,348,396,426,487,569,597,602,669,681,693,763,773,796,884,904,940,1034,1125,1136,1167,1210,1255,1271,1320,1353,1371,1420,1448,1544,1554],"knowledge":[21,312,1063],"interest":[24],"or":[25,571,825,987,1562,1600],"expectations":[26],"potential":[29,557],"community":[30,1254],"readers":[32,821],"gain":[34,464,1585],"benefit":[35,661,1495],"from":[36,93,662,786,1012,1496],"itself.":[39,418],"Michael":[40],"Piotrowski":[41,295,427,1333],"has":[42,61,178,192,261,591,724],"indeed":[43,922,1437],"managed":[44],"optimize":[46],"this":[47,353,639,658,920,1502,1632],"relation":[48],"by":[49,65,169,414,1019,1236,1291,1386],"bringing":[50],"public":[53],"compendium":[55],"information":[57,123,1542],"that":[58,286,302,351,441,495,622,628,654,718,801,820,895,955,999,1074,1249,1394,1429,1458,1478],"I":[59,300,454,849,1000,1058,1093,1454,1564,1579,1615],"think":[60,1627],"been":[62,179,815,931,1348,1365],"heavily":[63],"awaited":[64],"many":[66],"scholars":[67,1638],"having":[68,1592],"deal":[70,385],"with":[71,386,984,1109,1414,1612],"corpora":[72,1242,1270,1561],"historical":[74,89,275,375,402,424,472,506,783,887,1037,1134,1181,1203,1241,1269,1384,1451],"texts.":[75,507],"covers":[78,488,526,733,890],"most":[79,1029,1170,1219,1274,1292,1468,1575],"topics":[80,188,580,812,1477,1539],"related":[81,370,541],"acquisition,":[84],"encoding,":[85,710],"annotation":[87],"textual":[90,307],"data,":[91],"seen":[92],"point":[95,653,788],"view":[97,790],"linguistic":[100],"content.":[101,1473],"As":[102],"such,":[103],"it":[104,381,525,629,756,775,928,1002,1391,1430,1619],"does":[105],"not":[106,155,803,1206,1315,1322,1466],"address":[107],"issues":[108,369,540],"related,":[109],"for":[110,423,457,551,563,610,645,881,952,982,1036,1064,1117,1180,1222,1318,1440,1471,1508,1623,1637],"instance,":[111,611,1515],"editions":[114,1345],"these":[116,697,810,1629],"texts,":[117],"but":[118,1631],"conveys":[119],"wealth":[121],"on":[124,165,189,207,616,715,777,846,871,906,1042,1185,1198,1202,1287,1339,1351,1379,1444,1523,1596],"various":[126,368,489,546,552,579,892],"aspects":[127,490,673],"where":[128,1152],"recent":[129,1196],"developments":[130],"in":[131,149,184,266,277,290,321,361,374,390,406,459,468,479,637,665,676,782,805,823,861,926,992,1087,1105,1149,1175,1252,1267,1295,1516,1528,1552,1588,1628],"language":[132,258,314],"technology":[133],"may":[134,382,444,896,1191],"help":[135,1456],"digital":[136,267,1224],"humanities":[137,268],"projects":[138,176,282,350,537,1294],"be":[140,328,383,498,642,704,897,1048,1158,1193,1399,1438,1504,1634],"aware":[141],"current":[144,343,761,908,912],"state":[145],"art":[148],"field.Still,":[151],"encyclopedic":[157],"description":[158],"such":[160,262,1065,1472,1520,1645],"technologies.":[161],"It":[162,197,377,737,889,1068,1127,1245,1304],"based":[164],"acquired":[168],"author":[171,241,590,700,845,1076,1583,1625],"within":[172],"corpus":[174,284,504],"development":[175],"he":[177,191],"involved":[180],"in,":[181],"reflects":[183],"particular":[185,322,460,1040],"specific":[187,689,779],"which":[190,214,299,686,1313,1346,1527],"made":[193,1290],"more":[194,201,583,667,816,1072,1123,1498,1586],"in-depth":[195,603],"explorations.":[196],"thus":[199,1354],"written":[200],"as":[202,227,330,515,858,990,1061,1086,1279,1300,1433,1462,1481,1483,1521],"series":[204,229,975,1510],"returns":[206],"than":[209,1591],"systematic":[211],"resource":[212,1260],"one":[215,613,824,1013,1216,1572],"would":[216,455,660,1059,1094,1314,1321,1494,1503,1530,1584],"want":[217,1541],"return":[219],"after":[220],"its":[221,521,1020],"initial":[222],"reading.The":[223],"organized":[226],"nine":[231],"short":[232,452,977],"chapters.In":[233],"first":[235,466,738],"two":[236,357,688,1007],"(very":[237],"short)":[238],"chapters,":[239,340],"presents":[242,341,701],"general":[244,600],"scope":[245],"provides":[250,757,973,1282,1335],"overview":[252,576],"reasons":[255],"why":[256],"natural":[257],"processing":[259,315],"(NLP)":[260],"entrenched":[264],"position":[265,333],"at":[269,945,1183,1207],"large":[270],"study":[273],"text":[276,900,953,1135],"particular.":[278],"Citing":[279],"several":[280,1024],"prominent":[281],"initiatives":[285,347,941,1174],"have":[287,814,930,956,1027,1347,1364,1374],"taken":[288],"place":[289],"last":[292,1226],"few":[293],"decades,":[294],"defends":[296],"thesis,":[298],"share,":[301],"deep":[304],"understanding":[305,467,1263],"documents":[308],"requires":[309],"some":[310,433,1044,1357],"basic":[311],"methods":[316,981,1143],"techniques.":[318],"Chapter":[319,677,993,1015,1091,1113],"2":[320],"(\u201cNLP":[323,1115],"Digital":[325],"Humanities\u201d)":[326],"could":[327,641,703,828,1363,1565,1633],"read":[329,514],"autonomous":[332],"paper,":[334,1352],"which,":[335],"independently":[336],"following":[339,966],"landscape":[344],"infrastructural":[346],"shape":[352],"convergence":[354],"between":[355,599],"fields.Chapter":[358],"3":[359],"(\u201cSpelling":[360],"Historical":[362,483,1118],"Texts,\u201d":[363,484],"pp.":[364,485,684,971,1120,1230],"11\u201323)":[365],"describes":[366,1056],"spelling":[372,988],"variations":[373,989],"text.":[376,888],"shows":[378,1077,1246],"how":[379],"difficult":[380,512,584,1307],"both":[387,785,1262],"diachronic":[388],"(e.g.,":[389,766],"comparison":[391,544,618],"modern":[393,668],"standardized":[394],"spellings)":[395,403],"synchronic":[397],"(degree":[398],"stabilization":[400],"variations,":[404],"especially":[405],"context":[408,1151],"uncertainty":[411],"brought":[412,725],"about":[413,1543],"transcription":[416,794,883],"process":[417],"This":[419,447,649,833,1189],"particularly":[421],"true":[422],"manuscripts":[425],"goes":[428,623],"deeply":[429],"into":[430,624,759,1356],"this,":[431],"showing":[432],"concrete":[434,606,960,1139],"examples":[435],"kind":[438,450],"hurdles":[440],"scholar":[443],"fall":[445,1355],"into.":[446],"introduction":[453],"recommend":[456,1096],"anyone,":[458],"students,":[461],"wanting":[462],"domain":[470,1177],"spelling.Chapter":[473],"4":[474],"longest":[477],"chapter":[478,509,650,869,967,1162,1227,1278],"(\u201cAcquiring":[482],"25\u201352)":[486],"digitization":[493,536],"workflow":[494],"needs":[496],"set":[499,1009],"up":[500],"create":[502],"quite":[511,527,1010,1306],"single":[517,614],"unit":[518],"because":[519,585,1195,1423],"intrinsic":[522],"heterogeneity.":[523,1022],"Indeed,":[524,1501],"wide":[529],"range":[530],"topics:":[532],"presentation":[533,742],"existing":[535,1155],"worldwide,":[538],"technical":[539],"scanning,":[543],"optical":[547,564],"character":[548,565,692,709,747],"recognition":[549,566,1201],"systems":[550],"types":[553],"scripts,":[555],"role":[558,873],"lexical":[560],"resources,":[561],"crowdsourcing":[562],"(OCR)":[567],"post-processing,":[568],"manual":[570],"semi-automatic":[572],"keying.":[573],"Getting":[574],"even":[582],"way":[588],"followed":[592],"his":[593],"own":[594],"personal":[595],"experience,":[596],"alternates":[598],"considerations":[601],"presentations":[604],"results.":[607],"Pages":[608],"34\u201340,":[609],"subsection":[615,640],"OCR":[620,985],"outputs":[621],"so":[625,819,1427,1590],"much":[626],"detail":[627,1033,1488],"breaks":[630],"continuity":[632],"argument,":[635],"although":[636],"itself":[638,1018],"really":[643],"interesting":[644,932,1284,1337],"specialized":[647],"reader.":[648],"illustrates":[651],"content":[656,1425,1507,1569],"being":[663,855],"published":[664,856],"open":[670,1405],"setting.Data":[671],"representation":[672,893],"are":[674,802,1205,1211,1479,1640],"covered":[675],"5":[678],"(\u201cText":[679],"Encoding":[680,877],"Annotation":[682],"Schemes,\u201d":[683],"53\u201368),":[685],"tackles":[687],"issues,":[690],"namely,":[691,1331],"document":[694],"encoding.":[695],"On":[696,1328],"two,":[698],"what":[702,1057],"considered":[705],"best":[706,1654],"practices.":[707],"For":[708],"rightly":[713],"focuses":[714,776,870],"advantages":[717],"move":[720],"towards":[721],"ISO":[722,771],"10646/Unicode":[723],"community.":[728],"corresponding":[730,853,1547,1559],"sub-section":[731],"actually":[732],"three":[734,811],"different":[735,1492],"aspects:":[736],"makes":[739],"extensive":[741],"history":[745],"encoding":[748,764,885,944],"standards":[749,936],"(from":[750],"ASCII/ISO":[751],"646":[752],"Unicode/ISO":[754],"10646),":[755],"insights":[758],"coverage":[762],"principles":[765],"UTF-8":[767],"vs.":[768],"UTF-16)":[769],"10646,":[772],"finally,":[774],"difficulties":[780],"occurring":[781],"texts":[784,854,1038,1204],"legacy":[792],"ASCII-based":[793],"languages":[795],"management":[798],"characters":[800],"present":[804],"Unicode.":[806],"Although":[807,919],"well":[808,1165,1482],"documented,":[809],"should":[813,1373,1431],"clearly":[817],"separated":[818],"interested":[822,1533],"other":[827],"directly":[829],"refer":[830,934],"it.":[832],"typical":[836],"case":[837,1089],"where,":[838],"given":[839],"great":[841],"expertise":[842,1084],"subject,":[848],"can":[850,1157,1398],"imagine":[851,1310,1566],"on-line":[857,1560,1577],"separate":[859],"entries":[860,1513],"blog.":[863],"second":[865],"half":[866],"Text":[876],"Initiative":[878],"(TEI)":[879],"guidelines":[880,1299],"levels":[894],"concerned":[898],"(metadata,":[899],"structure,":[901],"surface":[902],"annotation)":[903],"insists":[905],"difficulty":[909,1341],"linking":[911],"NLP":[913],"tools":[914,1156],"TEI":[916,1298,1317,1326],"encoded":[917],"documents.":[918],"still":[923,1652],"issue":[925],"general,":[927],"might":[929],"(ISO":[937],"24611\u2013":[938],"MAF)":[939],"(Textgrid":[942],"core":[943],"token":[947],"level;":[948],"TXM":[950],"platform":[951],"mining)":[954],"started":[957],"provide":[959],"sustainable":[961],"answers":[962],"issue.The":[965],"(\u201cHandling":[968],"Spelling":[969],"Variations,\u201d":[970],"69\u201384),":[972],"studies":[978],"describing":[979],"possible":[980,1142],"dealing":[983],"errors":[986],"described":[991],"3.":[994],"Independent":[995],"fact":[998],"find":[1001],"strange":[1003],"see":[1005],"chapters":[1008,1493],"far":[1011],"another,":[1014],"6":[1016],"distinguishes":[1017],"profound":[1021],"Whereas":[1023],"sections":[1025,1045,1102],"do":[1026],"appropriate":[1030,1147,1404,1469],"level":[1031,1082,1486],"topicality":[1035],"(in":[1039],"those":[1041,1522],"canonicalization),":[1043],"seem":[1046],"completely":[1049],"off":[1050],"topic":[1051],"(Section":[1052],"6.2,":[1053],"\u201cEdit":[1054],"Distance,\u201d":[1055],"consider":[1060],"background":[1062,1259,1434],"book).":[1067],"all":[1070,1208],"disappointing":[1073],"here":[1078,1369],"very":[1080,1164],"high":[1081],"and,":[1085],"3,":[1092],"strongly":[1095],"reading":[1098],"relevant":[1101,1173,1275,1555],"newcomers":[1104],"field.In":[1107],"contrast":[1108],"previous":[1111],"chapter,":[1112],"7":[1114],"Tools":[1116],"Languages,\u201d":[1119],"85\u2013100)":[1121],"coherent":[1124],"focused.":[1126],"mainly":[1128],"addresses":[1129],"morpho-syntactic":[1131],"analysis":[1132,1338],"presents,":[1137],"through":[1138,1490],"deployment":[1140],"scenarios,":[1141],"constrain":[1145],"parsers,":[1148],"hardly":[1153],"any":[1154,1380,1441],"simply":[1159],"re-used.":[1160],"documented":[1166],"refers":[1168],"morphology":[1179],"text,":[1182],"least":[1184],"European":[1187],"scene.":[1188],"focus":[1190],"also":[1192,1334],"misleading":[1194],"work":[1197,1443],"named":[1199],"entity":[1200],"mentioned":[1209],"probably,":[1212],"my":[1214],"view,":[1215],"promising":[1220],"direction":[1221],"enhanced":[1223],"scholarship.The":[1225],"(\u201cHistorical":[1228],"Corpora,\u201d":[1229],"101\u2013116)":[1231],"compendium,":[1234],"sorted":[1235],"language,":[1237],"major":[1240],"available":[1243],"worldwide.":[1244],"dynamic":[1248],"currently":[1250],"exists":[1251],"essential":[1258],"who":[1264,1639],"active":[1266],"maintaining":[1268],"discerning":[1272],"resources.":[1276,1578],"whole":[1281],"\u201chistorical\u201d":[1285],"perspective":[1286],"progress":[1289],"text-based":[1293],"using":[1296],"reference":[1302,1435],"standard.":[1303],"seems":[1305],"now":[1308,1641],"initiative":[1312],"take":[1316],"granted,":[1319],"build":[1323],"inside":[1324],"framework.":[1327],"another":[1329],"issue,":[1330],"copyright,":[1332],"re-using":[1343],"old":[1344],"recently":[1349],"re-edited":[1350],"publisher's":[1358],"copyright":[1359,1608],"restrictions.":[1360],"conclusion":[1362],"little":[1367],"tougher":[1368],"though,":[1370],"probably":[1372],"recommended":[1375],"putting":[1376],"hold":[1378],"paper":[1381],"sources":[1385],"private":[1388],"publisher":[1389],"unless":[1390],"guaranteed":[1393],"electronic":[1396],"material":[1397,1594],"used":[1400],"freely,":[1401],"under":[1402],"license.As":[1406],"whole,":[1408],"leaves":[1411],"reader":[1413,1534],"mixed":[1416],"feeling":[1417],"enthusiasm":[1419],"disappointment.":[1421],"Enthusiasm,":[1422],"rich":[1428],"serve":[1432],"(and":[1436],"quoted)":[1439],"further":[1442],"creation,":[1446],"management,":[1447],"curation":[1449],"corpora.":[1452],"Still,":[1453],"cannot":[1455,1616],"thinking":[1457],"editorial":[1460],"setting":[1461,1470],"variety":[1475],"addressed":[1480],"heterogeneous":[1485],"provided":[1489],"fragmented":[1499],"treatment.":[1500],"perfect":[1506],"blog":[1512,1519],"(for":[1514],"hypotheses.org":[1525],"platform)":[1526],"turn":[1529],"allow":[1531],"discover":[1536],"exactly":[1537],"they":[1540],"cite":[1545],"entries.":[1548],"With":[1549],"bibliography":[1551],"Zotero":[1553],"pointers":[1556],"tools,":[1563],"resulting":[1568],"soon":[1570],"becoming":[1571],"cited":[1576],"am":[1580],"sure":[1581],"visibility":[1587],"doing":[1589],"hidden":[1595],"library":[1598],"shelf":[1599],"behind":[1601],"paywall.":[1603],"Not":[1604],"knowing":[1605],"exact":[1607],"transfer":[1609],"agreement":[1610],"associated":[1611],"book,":[1614],"judge":[1617],"if":[1618],"too":[1621],"late":[1622],"terms,":[1630],"lesson":[1636],"planning":[1642],"write":[1644],"introductory":[1647],"publication.":[1648],"Is":[1649],"medium?":[1655]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
