{"id":"https://openalex.org/W2544444394","doi":null,"title":"Improving dependency parsing using word clusters","display_name":"Improving dependency parsing using word clusters","publication_year":2015,"publication_date":"2015-10-22","ids":{"openalex":"https://openalex.org/W2544444394","mag":"2544444394"},"language":"en","primary_location":{"id":"pmh:oai:www.duo.uio.no:10852/43834","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/43834","pdf_url":"http://hdl.handle.net/10852/43834","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"","raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10852/43834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029165575","display_name":"Jostein Lien","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jostein Lien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5029165575"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/dependency-parsing","display_name":"dependency parsing","score":0.8040000200271606},{"id":"https://openalex.org/keywords/word-clusters","display_name":"word clusters","score":0.7979999780654907},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9729999899864197},{"id":"https://openalex.org/keywords/maltparser","display_name":"MaltParser","score":0.9340000152587891},{"id":"https://openalex.org/keywords/transition-based-parsing","display_name":"transition-based parsing","score":0.8100000023841858},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.925000011920929},{"id":"https://openalex.org/keywords/feature-expansion","display_name":"feature expansion","score":0.597000002861023},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6840000152587891},{"id":"https://openalex.org/keywords/wall-street-journal","display_name":"Wall Street Journal","score":0.8479999899864197},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.7519999742507935},{"id":"https://openalex.org/keywords/unlabeled-text","display_name":"unlabeled text","score":0.38100001215934753},{"id":"https://openalex.org/keywords/constituency-parsing","display_name":"constituency parsing","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.8833716511726379},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7178231477737427},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7110650539398193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688910722732544},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6342698931694031},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6012662053108215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089988708496094},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.47218242287635803},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.30332618951797485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27053630352020264},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:www.duo.uio.no:10852/43834","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/43834","pdf_url":"http://hdl.handle.net/10852/43834","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"","raw_type":"info:eu-repo/semantics/masterThesis"},{"id":"mag:2544444394","doi":null,"is_oa":false,"landing_page_url":"https://www.duo.uio.no/handle/10852/43834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:www.duo.uio.no:10852/43834","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/43834","pdf_url":"http://hdl.handle.net/10852/43834","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"","raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2544444394.pdf","grobid_xml":"https://content.openalex.org/works/W2544444394.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W130850236","https://openalex.org/W158861739","https://openalex.org/W191422183","https://openalex.org/W194033037","https://openalex.org/W1521190430","https://openalex.org/W1521626219","https://openalex.org/W1532325895","https://openalex.org/W1535015163","https://openalex.org/W1549998098","https://openalex.org/W1591659308","https://openalex.org/W2008652694","https://openalex.org/W2027979924","https://openalex.org/W2070523965","https://openalex.org/W2092286949","https://openalex.org/W2096044384","https://openalex.org/W2101234009","https://openalex.org/W2105103433","https://openalex.org/W2109955707","https://openalex.org/W2121227244","https://openalex.org/W2128634885","https://openalex.org/W2139621418","https://openalex.org/W2142838865","https://openalex.org/W2183292753","https://openalex.org/W2251869015","https://openalex.org/W2569308312"],"related_works":["https://openalex.org/W2128976668","https://openalex.org/W2128634885","https://openalex.org/W8788258","https://openalex.org/W2115847145","https://openalex.org/W2384666924","https://openalex.org/W2138321806","https://openalex.org/W2250525544","https://openalex.org/W2525024326","https://openalex.org/W1973346430","https://openalex.org/W1561058873"],"abstract_inverted_index":{"This":[0],"thesis":[1,340],"describes":[2],"a":[3,18,44,67,96,127],"semi-supervised":[4,118],"approach":[5],"to":[6,63,131],"improving":[7],"statistical":[8],"dependency":[9,21,68,83,602,630,658,685,715,927,960,986,1016,1032,1053,1083,1174,1192],"parsing":[10,123,275,378,488,514,539,562,595,624,652,678,770,795,818,839,855,901,953,979,1005,1021,1046,1074,1105,1162,1179,1224,1271,1290,1293,1308,1311],"using":[11,25,32,95,126,135,926],"word":[12,78],"clusters":[13,40,79,93,1297,1315],"as":[14,43],"features":[15,28,226,241,496,521,546,570,603,631,659,686,734,777,802,850,867,911,920,928,961,987,1017,1033,1054,1084,1175],"in":[16,49,338],"MaltParser,":[17],"data-driven":[19],"transition-based":[20],"parser.We":[22],"experiment":[23],"with":[24,89,108,182,820,841,856,1007,1023,1292,1300,1310,1318],"different":[26],"clustering":[27,193,202,225,240,352,461,492,517,542,566,599,627,655,682,720,733,741,773,798,825,846,863,905,957,983,1013,1029,1050,1078,1109,1147,1166,1183,1228,1278],"for":[29,76,351,373,377,391,456,740,922,1142],"generating":[30,66,77],"clusters,":[31],"the":[33,37,56,71,87,102,132,430,445,1008,1024],"minibatch":[34],"variant":[35],"of":[36,46,70,117,142,148,157,168,195,293,312,331,732],"K-means":[38,1275],"algorithm.The":[39],"are":[41],"used":[42,54,75,337],"source":[45],"additional":[47],"information":[48,90],"an":[50,115],"expanded":[51,107],"feature":[52,98,104,111,335,829],"model":[53,822,843,1010,1026],"by":[55,94],"MaltParser":[57,274,334],"system.A":[58],"baseline":[59,103,133],"parser":[60,88,129],"is":[61,73],"applied":[62],"unlabeled":[64,737,923],"text,":[65],"representation":[69],"text.K-means":[72],"then":[74,85],"based":[80,564,680,735,823,844,861,903,955,981,1011,1027,1048,1076,1107,1164,1181,1190,1226,1273,1294,1312],"on":[81,91,487,494,513,519,538,544,565,568,594,601,623,629,651,657,681,684,736,769,775,794,800,824,827,845,848,862,865,904,909,952,956,959,978,982,985,1012,1015,1028,1031,1049,1052,1077,1082,1108,1165,1173,1182,1191,1227,1274,1279,1295,1313],"this":[82,114,339],"representation.We":[84],"re-train":[86],"these":[92],"cluster-informed":[97,128],"model,":[99],"having":[100],"all":[101,1094,1110,1234],"functions,":[105,112],"but":[106],"addition":[109],"cluster":[110,183],"making":[113],"instance":[116],"learning.We":[119],"report":[120],"significantly":[121],"improved":[122],"results":[124,486,512,537,563,593,622,650,679,713,768,793,819,840,902,951,977,1006,1022,1047,1075,1099,1106,1163,1180,1225,1272,1291,1309],"when":[125,719],"compared":[130],"parser,":[134],"both":[136],"in-domain":[137,826,847,864,908,958,984,1014,1030,1081,1097,1135,1189],"and":[138,716,858,907,1080,1096,1134,1150,1168,1185,1230,1276],"out-of-domain":[139],"data.iii":[140],"List":[141,330],"Figures2.1":[143],"Constituent":[144],"parse":[145],"tree":[146],"example":[147,156,167,180,194,203,227,242,254,276,277,292,311],"sentence":[149,158,169],"from":[150,159,170,197,429,444,459,491,516,541,598,626,654,772,797,1145,1171,1188,1233,1282],"Reuters":[151,160,171,198,431,493,518,543,567,600,628,656,683,721,906,1079,1095,1172,1283],".":[152,161,162,163,172,173,174,175,176,185,186,187,188,189,190,199,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,228,229,230,231,232,233,234,235,236,237,243,244,245,246,247,248,249,250,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,278,279,280,281,282,283,284,285,286,287,288,289,298,299,300,301,302,303,304,305,306,307,308,317,318,319,320,321,322,323,324,325,326,327,341,342,343,344,345,346,347,348,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,379,380,381,382,383,384,385,386,387,388,396,397,398,399,400,401,402,403,404,405,406,407,408,418,419,420,421,422,423,424,433,434,435,436,437,438,439,449,450,451,452,464,465,466,467,468,469,470,471,472,473,474,475,476,477,478,479,480,481,482,483,497,498,499,500,501,502,503,504,505,506,507,508,509,522,523,524,525,526,527,528,529,530,531,532,533,534,547,548,549,550,551,552,553,554,555,556,557,558,559,571,572,573,574,575,576,577,578,579,580,581,582,583,584,585,586,587,588,589,590,604,605,606,607,608,609,610,611,612,613,614,615,616,617,618,619,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,660,661,662,663,664,665,666,667,668,669,670,671,672,673,674,675,687,688,689,690,691,692,693,694,695,696,697,698,699,700,701,702,703,704,705,706,707,708,709,722,723,724,725,726,727,728,729,742,743,744,745,746,747,748,749,750,751,752,753,754,755,756,757,758,759,760,761,762,763,764,765,778,779,780,781,782,783,784,785,786,787,788,789,790,803,804,805,806,807,808,809,810,811,812,813,814,815,830,831,832,833,834,835,868,869,870,871,872,873,874,875,876,877,878,879,880,881,882,883,884,885,886,887,888,889,890,891,892,893,894,895,896,897,912,913,914,915,916,917,929,930,931,932,933,934,935,936,937,938,939,940,941,942,943,944,945,946,947,948,962,963,964,965,966,967,968,969,970,971,972,973,974,988,989,990,991,992,993,994,995,996,997,998,999,1000,1001,1002,1034,1035,1036,1037,1038,1039,1040,1041,1042,1055,1056,1057,1058,1059,1060,1061,1062,1063,1064,1065,1066,1067,1068,1069,1070,1085,1086,1087,1088,1089,1090,1091,1100,1101,1114,1115,1116,1117,1118,1119,1120,1121,1122,1123,1124,1125,1126,1127,1128,1129,1137,1138,1153,1154,1155,1156,1157,1158,1194,1195,1196,1197,1198,1199,1200,1201,1202,1203,1204,1205,1206,1207,1208,1209,1210,1211,1212,1213,1214,1215,1216,1217,1218,1219,1220,1238,1239,1240,1241,1242,1243,1244,1245,1246,1247,1248,1249,1250,1251,1252,1253,1254,1255,1256,1257,1258,1259,1260,1261,1262,1263,1264,1265,1266,1267,1284,1285],".2.2":[153],"Dependency":[154,224],"graph":[155],".2.3":[164],"CoNLL":[165],"format":[166],".2.4":[177],"ConLL":[178],"file":[179],"annotated":[181],"labels":[184],".3.1":[191],"Hierarchical":[192],"lemmas":[196,428,443,463,1152,1170,1187,1232,1281],".3.2":[200],"Brown":[201,1296,1314],".6.1":[223,425],".6.2":[238,440],"Path-to-root-pos":[239],".6.3":[251,453],"Maltparser":[252],"training":[253],".6.4":[273,484],".6.5":[290,510],"Clustering":[291,310,919],"web":[294,313],"data":[295,314,353,375,739,925],"-part":[296,315],"1":[297],".6.6":[309,535],"2":[316],".v":[328],"vi":[329],"Tables":[332],"2.1":[333],"models":[336,860],".5.1":[349],"Statistics":[350,372,390],"sets":[354,376],".5.2":[371],"SANCL":[374,447,738,924,1111,1133,1235],".5.3":[389],"Wall":[392],"Street":[393],"Journal":[394],"split":[395],".5.4":[409],"Parsing":[410,454,1140],"scores":[411,455,1141],"comparing":[412,1148],"gold":[413,1301],"vs":[414],"auto":[415,1319],"Pos":[416],"tags":[417,1303,1321],"Most":[426,441],"frequent":[427,442],"corpus":[432,448],"All":[446,1132],"assessing":[457,1143],"impact":[458,1144],"non-deterministic":[460,1146],"50,000":[462,1151,1169,1186,1231],"Development":[485,511,536,592,621,649,767,792,950,976],"WSJ":[489,596],"22":[490,597],"path-to-root-pos":[495,520,545,569,776,801,828,849],"Weblogs":[515,625,771,954],"Emails":[540,653,796,980],".6.7":[560],"Held-out":[561,677,817,838,1004,1020],".6.8":[591],".6.9":[620],".6.10":[648],".6.11":[676],".6.12":[710],"Comparing":[711,853,899,1044,1072,1093,1103,1131,1160,1177,1222,1269,1287,1305],"held-out":[712,854,900,1045,1073,1098,1104,1161,1178,1223,1270,1289,1307],"between":[714],"pathto-root-pos":[717],"geatures":[718],".6.13":[730],"Number":[731],".6.14":[766],"indomain":[774,799,1051],".6.15":[791],".6.16":[816],"Form_simple":[821,857,1009],".vii":[836],"6.17":[837],"Form_all":[842,859,1025],"form-all":[851],".6.18":[852],"path-root-pos":[866,910],".6.19":[898],".6.20":[918],"statistics":[921],".6.21":[949],".6.22":[975],".6.23":[1003],"form-simple":[1018],"6.24":[1019],".6.25":[1043],".6.26":[1071],".6.27":[1092],".6.28":[1102],"domains":[1112,1236],"concatenated":[1113,1237],".6.29":[1130],"held-out-results":[1136],".6.30":[1139],"10,000":[1149,1167,1184,1229],".6.31":[1159],"6.32":[1176],"features.":[1193],".6.33":[1221],".6.34":[1268],"agglomerative":[1277],"5,000":[1280],".6.35":[1286],"our":[1288,1306],"(\u00d8vrelid,":[1298,1316],"Skj\u00e6rholt)":[1299,1317],"PoS":[1302,1320],".6.36":[1304],".viii":[1322]},"counts_by_year":[],"updated_date":"2026-09-03T10:48:47.769340","created_date":"2016-11-04T00:00:00"}