{"id":"https://openalex.org/W2794904608","doi":"https://doi.org/10.18653/v1/n18-2075","title":"Text Segmentation as a Supervised Learning Task","display_name":"Text Segmentation as a Supervised Learning Task","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2794904608","doi":"https://doi.org/10.18653/v1/n18-2075","mag":"2794904608"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n18-2075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2075","pdf_url":"https://www.aclweb.org/anthology/N18-2075.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N18-2075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025006463","display_name":"Omri Koshorek","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Omri Koshorek","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel","Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038761180","display_name":"Adir Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Adir Cohen","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068333527","display_name":"Noam Mor","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Noam Mor","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007295855","display_name":"Michael Rotman","orcid":"https://orcid.org/0000-0003-0342-125X"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Rotman","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel","Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045872048","display_name":"Jonathan Berant","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan Berant","raw_affiliation_strings":["School of Computer Science Tel-Aviv University, Israel","Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science Tel-Aviv University, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025006463"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.38993721,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83272688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"473"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9937000274658203,"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/segmentation","display_name":"Segmentation","score":0.8442490696907043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7429733276367188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7116806507110596},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.617990255355835},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6087859869003296},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5873662829399109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5497381091117859},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5315214395523071},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.48565638065338135},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.45564043521881104},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4444717466831207},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.39844873547554016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3935825824737549},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39219385385513306},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3529641628265381},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08869698643684387}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8442490696907043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429733276367188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7116806507110596},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.617990255355835},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6087859869003296},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5873662829399109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5497381091117859},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5315214395523071},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.48565638065338135},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.45564043521881104},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4444717466831207},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.39844873547554016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3935825824737549},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39219385385513306},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3529641628265381},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08869698643684387},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/n18-2075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2075","pdf_url":"https://www.aclweb.org/anthology/N18-2075.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.09337","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09337","pdf_url":"https://arxiv.org/pdf/1803.09337","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2794904608","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1803.09337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1803.09337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.09337","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/n18-2075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2075","pdf_url":"https://www.aclweb.org/anthology/N18-2075.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2794904608.pdf","grobid_xml":"https://content.openalex.org/works/W2794904608.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1521626219","https://openalex.org/W1626945812","https://openalex.org/W1862888253","https://openalex.org/W1880262756","https://openalex.org/W2017776283","https://openalex.org/W2080179128","https://openalex.org/W2148818577","https://openalex.org/W2154593091","https://openalex.org/W2949496004"],"related_works":["https://openalex.org/W2962716111","https://openalex.org/W2378193718","https://openalex.org/W2118405289","https://openalex.org/W2961204630","https://openalex.org/W3198035914","https://openalex.org/W2132048049","https://openalex.org/W2606129492","https://openalex.org/W2132551375","https://openalex.org/W2273169465","https://openalex.org/W1545666865","https://openalex.org/W3204594274","https://openalex.org/W2402385743","https://openalex.org/W1988460048","https://openalex.org/W1992237336","https://openalex.org/W2350231396","https://openalex.org/W1886814818","https://openalex.org/W2756894687","https://openalex.org/W2358469450","https://openalex.org/W2036115071","https://openalex.org/W2336568965"],"abstract_inverted_index":{"Text":[0],"segmentation,":[1],"the":[2,40],"task":[3],"of":[4],"dividing":[5],"a":[6,17,53,59,77],"document":[7],"into":[8],"contiguous":[9],"segments":[10],"based":[11,80],"on":[12,25,29,81],"its":[13],"semantic":[14],"structure,":[15],"is":[16,67],"longstanding":[18],"challenge":[19],"in":[20,42],"language":[21],"understanding.":[22],"Previous":[23],"work":[24],"text":[26,50,64],"segmentation":[27,51,65,78],"focused":[28],"unsupervised":[30],"methods":[31],"such":[32],"as":[33,52],"clustering":[34],"or":[35],"graph":[36],"search,":[37],"due":[38],"to":[39,90],"paucity":[41],"labeled":[43,71],"data.":[44],"In":[45],"this":[46,82],"work,":[47],"we":[48,75],"formulate":[49],"supervised":[54],"learning":[55],"problem,":[56],"and":[57,70,84],"present":[58],"large":[60],"new":[61],"dataset":[62,83],"for":[63],"that":[66,86],"automatically":[68],"extracted":[69],"from":[72],"Wikipedia.":[73],"Moreover,":[74],"develop":[76],"model":[79],"show":[85],"it":[87],"generalizes":[88],"well":[89],"unseen":[91],"natural":[92],"text.":[93]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
