{"id":"https://openalex.org/W2106237193","doi":"https://doi.org/10.18653/v1/d13-1146","title":"Elephant: Sequence Labeling for Word and Sentence Segmentation","display_name":"Elephant: Sequence Labeling for Word and Sentence Segmentation","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2106237193","doi":"https://doi.org/10.18653/v1/d13-1146","mag":"2106237193"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1146","pdf_url":"https://aclanthology.org/D13-1146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1146.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052327595","display_name":"Kilian Evang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kilian Evang","raw_affiliation_strings":["Computational Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics","institution_ids":["https://openalex.org/I2802799214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071473719","display_name":"Valerio Basile","orcid":"https://orcid.org/0000-0001-8110-6832"},"institutions":[{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerio Basile","raw_affiliation_strings":["Computational Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics","institution_ids":["https://openalex.org/I2802799214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022698890","display_name":"Grzegorz Chrupa\u0142a","orcid":"https://orcid.org/0000-0001-9498-6912"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Grzegorz Chrupa\u0142a","raw_affiliation_strings":["Tilburg Univ, Tilburg University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tilburg Univ, Tilburg University","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002288369","display_name":"Johan Bos","orcid":"https://orcid.org/0000-0002-9079-5438"},"institutions":[{"id":"https://openalex.org/I2802799214","display_name":"Association for Computational Linguistics","ror":"https://ror.org/019sw1443","country_code":"US","type":"other","lineage":["https://openalex.org/I2802799214"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johan Bos","raw_affiliation_strings":["Computational Linguistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics","institution_ids":["https://openalex.org/I2802799214"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6609,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94521425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1422","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sequence-labeling","display_name":"Sequence labeling","score":0.8690282702445984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.824755847454071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.766498327255249},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7001819610595703},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6996028423309326},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6922386288642883},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6010324954986572},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5610395669937134},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5373363494873047},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5262075066566467},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5034629702568054},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46750199794769287},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4531042277812958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.345331609249115},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15767303109169006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08629176020622253}],"concepts":[{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.8690282702445984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824755847454071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.766498327255249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7001819610595703},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6996028423309326},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6922386288642883},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6010324954986572},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5610395669937134},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5373363494873047},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5262075066566467},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5034629702568054},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46750199794769287},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4531042277812958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.345331609249115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15767303109169006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08629176020622253},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.18653/v1/d13-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1146","pdf_url":"https://aclanthology.org/D13-1146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:tilburguniversity.edu:openaire_cris_publications/20178076-b1fe-4ed4-97f2-45a2ffcc97de","is_oa":false,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/20178076-b1fe-4ed4-97f2-45a2ffcc97de","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Evang, K, Basile, V, Chrupala, G & Bos, J 2013, Elephant: Sequence Labeling for Word and Sentence Segmentation. in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), Seattle, Washington, USA, pp. 1422-1426, EMNLP 2013: Conference on Empirical Methods in Natural Language Processing, Seattle, United States, 18/10/13. < http://www.aclweb.org/anthology/D13-1146 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:iris.unito.it:2318/1698244","is_oa":true,"landing_page_url":"http://hdl.handle.net/2318/1698244","pdf_url":"http://hdl.handle.net/2318/1698244","source":{"id":"https://openalex.org/S4306400637","display_name":"Institutional Research Information System University of Turin (University of Turin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I55143463","host_organization_name":"University of Turin","host_organization_lineage":["https://openalex.org/I55143463"],"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/conferenceObject"},{"id":"pmh:uvt:oai:tilburguniversity.edu:publications/2efe27dc-1ed0-4380-a428-c154bb47caa2","is_oa":false,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/2efe27dc-1ed0-4380-a428-c154bb47caa2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TITLE=None","raw_type":"info:eu-repo/semantics/other"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.3495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.3495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1146.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01344500v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01344500","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EMNLP 2013, Oct 2013, Seattle, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:tilburguniversity.edu:publications/20178076-b1fe-4ed4-97f2-45a2ffcc97de","is_oa":true,"landing_page_url":"http://www.aclweb.org/anthology/D13-1146","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Evang, K, Basile, V, Chrupala, G & Bos, J 2013, Elephant: Sequence Labeling for Word and Sentence Segmentation. in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (ACL), Seattle, Washington, USA, pp. 1422-1426, EMNLP 2013: Conference on Empirical Methods in Natural Language Processing, Seattle, United States, 18/10/13. < http://www.aclweb.org/anthology/D13-1146 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:rug:oai:pure.rug.nl:publications/a08d0970-e7ea-47f8-b2f5-f635109e29fd","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/a08d0970-e7ea-47f8-b2f5-f635109e29fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the EMNLP 2013: Conference on Empirical Methods in Natural Language Processing","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1146","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1146","pdf_url":"https://aclanthology.org/D13-1146.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2106237193.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W103905824","https://openalex.org/W179875071","https://openalex.org/W182831726","https://openalex.org/W1490831147","https://openalex.org/W1491598715","https://openalex.org/W1579838312","https://openalex.org/W1999051122","https://openalex.org/W2018560257","https://openalex.org/W2087946919","https://openalex.org/W2095726049","https://openalex.org/W2104071081","https://openalex.org/W2110485445","https://openalex.org/W2121764873","https://openalex.org/W2127973959","https://openalex.org/W2138181100","https://openalex.org/W2147880316","https://openalex.org/W2160986985","https://openalex.org/W2250741443","https://openalex.org/W2782445378","https://openalex.org/W3143104624","https://openalex.org/W3145383970"],"related_works":["https://openalex.org/W4322096459","https://openalex.org/W4379251483","https://openalex.org/W2379663637","https://openalex.org/W155626099","https://openalex.org/W2559372221","https://openalex.org/W2144950812","https://openalex.org/W2102131353","https://openalex.org/W3089147131","https://openalex.org/W3212884798","https://openalex.org/W4289548496"],"abstract_inverted_index":{"Tokenization":[0],"is":[1,37,41,60,83],"widely":[2],"regarded":[3],"as":[4],"a":[5,38],"solved":[6],"problem":[7,39],"due":[8],"to":[9,22,43,50,110,120],"the":[10,33,71,91,95,102,131],"high":[11],"accuracy":[12],"that":[13,40,79],"rule-based":[14,18],"tokenizers":[15,19],"achieve.":[16],"But":[17],"are":[20,57,98],"hard":[21],"maintain":[23],"and":[24,125,140],"their":[25],"rules":[26],"language":[27],"specific.":[28],"Like":[29],"an":[30,62],"elephant":[31],"in":[32,70,88,101],"living":[34],"room,":[35],"it":[36],"impossible":[42],"overlook":[44],"whenever":[45],"new":[46],"raw":[47],"datasets":[48],"need":[49],"be":[51],"processed":[52],"or":[53],"when":[54],"tokenization":[55],"conventions":[56],"reconsidered.":[58],"It":[59],"moreover":[61],"important":[63],"problem,":[64],"because":[65],"any":[66],"errors":[67],"occurring":[68],"early":[69],"pipeline":[72],"affect":[73],"further":[74],"analysis":[75],"negatively.":[76],"We":[77,97],"believe":[78],"regarding":[80],"tokenization,":[81],"there":[82],"still":[84],"room":[85],"for":[86],"improvement,":[87],"particular":[89],"on":[90],"methodological":[92],"side":[93],"of":[94],"task.":[96],"particularly":[99],"interested":[100],"following":[103],"questions:":[104],"Can":[105,114,128,136],"we":[106,115,129,137],"use":[107,116,130],"supervised":[108],"learning":[109,119],"avoid":[111],"hand-crafting":[112],"rules?":[113],"unsupervised":[117],"feature":[118,122],"reduce":[121],"engineering":[123],"effort":[124],"boost":[126],"performance?":[127],"same":[132],"method":[133],"across":[134],"languages?":[135],"combine":[138],"word":[139],"sentence":[141],"boundary":[142],"detection":[143],"into":[144],"one":[145],"task?":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}