{"id":"https://openalex.org/W2989200142","doi":"https://doi.org/10.18653/v1/k19-1054","title":"BeamSeg: A Joint Model for Multi-Document Segmentation and Topic Identification","display_name":"BeamSeg: A Joint Model for Multi-Document Segmentation and Topic Identification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989200142","doi":"https://doi.org/10.18653/v1/k19-1054","mag":"2989200142"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1054","pdf_url":"https://www.aclweb.org/anthology/K19-1054.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K19-1054.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066439336","display_name":"Pedro Mota","orcid":"https://orcid.org/0000-0002-1003-5640"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]},{"id":"https://openalex.org/I203847022","display_name":"Instituto Polit\u00e9cnico de Lisboa","ror":"https://ror.org/04ea70f07","country_code":"PT","type":"education","lineage":["https://openalex.org/I203847022"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["PT","US"],"is_corresponding":false,"raw_author_name":"Pedro Mota","raw_affiliation_strings":["INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","INESC-ID","Instituto Superior T\u00e9cnico Lisboa, Portugal","Carnegie Mellon University Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"INESC-ID","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I203847022","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","orcid":null},"institutions":[{"id":"https://openalex.org/I203847022","display_name":"Instituto Polit\u00e9cnico de Lisboa","ror":"https://ror.org/04ea70f07","country_code":"PT","type":"education","lineage":["https://openalex.org/I203847022"]},{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT","US"],"is_corresponding":false,"raw_author_name":"Maxine Eskenazi","raw_affiliation_strings":["Instituto Superior T\u00e9cnico Lisboa, Portugal","Carnegie Mellon University Pittsburgh, PA, USA","INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","INESC-ID"],"affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I203847022","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"INESC-ID","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067178556","display_name":"Lu\u00edsa Coheur","orcid":"https://orcid.org/0000-0002-2456-5028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I203847022","display_name":"Instituto Polit\u00e9cnico de Lisboa","ror":"https://ror.org/04ea70f07","country_code":"PT","type":"education","lineage":["https://openalex.org/I203847022"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT","US"],"is_corresponding":true,"raw_author_name":"Lu\u00edsa Coheur","raw_affiliation_strings":["Instituto Superior T\u00e9cnico Lisboa, Portugal","INESC-ID","INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","Carnegie Mellon University Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I203847022","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"INESC-ID","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"INESC-ID Instituto Superior T\u00e9cnico Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Carnegie Mellon University Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067178556"],"corresponding_institution_ids":["https://openalex.org/I121345201","https://openalex.org/I203847022","https://openalex.org/I4387152517","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.3006,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86017089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8624178171157837},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6836948394775391},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6627789735794067},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6623092889785767},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.6475244164466858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6399984359741211},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5649893879890442},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5612072944641113},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5352827310562134},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4461482763290405},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4288389980792999},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2224578857421875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07201451063156128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8624178171157837},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6836948394775391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6627789735794067},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6623092889785767},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.6475244164466858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399984359741211},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5649893879890442},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5612072944641113},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5352827310562134},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4461482763290405},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4288389980792999},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2224578857421875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07201451063156128},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k19-1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1054","pdf_url":"https://www.aclweb.org/anthology/K19-1054.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1054","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1054","pdf_url":"https://www.aclweb.org/anthology/K19-1054.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G3284537356","display_name":null,"funder_award_id":"SFRH/B","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5818630289","display_name":null,"funder_award_id":"SFRH/BD/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6700943011","display_name":null,"funder_award_id":"UID/CEC/50021/2019","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G724804869","display_name":null,"funder_award_id":"SFRH/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320319180","display_name":"Carnegie Mellon Portugal","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989200142.pdf","grobid_xml":"https://content.openalex.org/works/W2989200142.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W1592823049","https://openalex.org/W1626945812","https://openalex.org/W1663973292","https://openalex.org/W1723619723","https://openalex.org/W1828401780","https://openalex.org/W1862888253","https://openalex.org/W1880262756","https://openalex.org/W1983814883","https://openalex.org/W1989879829","https://openalex.org/W2015933299","https://openalex.org/W2027823133","https://openalex.org/W2043406630","https://openalex.org/W2067002391","https://openalex.org/W2069207503","https://openalex.org/W2072240081","https://openalex.org/W2072644219","https://openalex.org/W2089094722","https://openalex.org/W2092062917","https://openalex.org/W2106918957","https://openalex.org/W2112050062","https://openalex.org/W2118612506","https://openalex.org/W2124585778","https://openalex.org/W2128709346","https://openalex.org/W2137320444","https://openalex.org/W2141403362","https://openalex.org/W2144092076","https://openalex.org/W2148374900","https://openalex.org/W2154593091","https://openalex.org/W2159083595","https://openalex.org/W2165232124","https://openalex.org/W2303837218","https://openalex.org/W2739675333","https://openalex.org/W2741172726","https://openalex.org/W2758753219","https://openalex.org/W2809054113","https://openalex.org/W2914694065","https://openalex.org/W2962716111","https://openalex.org/W2963271397","https://openalex.org/W4231510805","https://openalex.org/W4234180827","https://openalex.org/W4293585212"],"related_works":["https://openalex.org/W2031284124","https://openalex.org/W2110027950","https://openalex.org/W142374489","https://openalex.org/W2250993361","https://openalex.org/W1979469248","https://openalex.org/W4253421417","https://openalex.org/W2043781532","https://openalex.org/W2148086098","https://openalex.org/W4361864099","https://openalex.org/W2145768976"],"abstract_inverted_index":{"We":[0,92],"propose":[1],"BeamSeg,":[2],"a":[3,36,97],"joint":[4],"model":[5,18,44,59],"for":[6],"segmentation":[7,147],"and":[8,89,141,148],"topic":[9,34,149],"identification":[10],"of":[11,116,134,137],"documents":[12,117],"from":[13,55,107],"the":[14,32,41,56,62,78,146],"same":[15,33,57,63],"domain.":[16],"The":[17,43,124],"assumes":[19],"that":[20,29,71,101,153],"lexical":[21,38,46],"cohesion":[22,47],"can":[23],"be":[24,87,157],"observed":[25],"across":[26],"documents,":[27],"meaning":[28],"segments":[30,60,83],"describing":[31],"use":[35],"similar":[37],"distribution":[39],"over":[40],"vocabulary.":[42],"implements":[45],"in":[48,81,129,145],"an":[49],"unsupervised":[50],"Bayesian":[51],"setting":[52],"by":[53,95],"drawing":[54],"language":[58,72],"with":[61],"topic.":[64],"Contrary":[65],"to":[66,86,139],"previous":[67],"approaches,":[68],"we":[69],"assume":[70],"models":[73,112],"are":[74,84,143],"not":[75,90],"independent,":[76],"since":[77],"vocabulary":[79],"changes":[80],"consecutive":[82],"expected":[85],"smooth":[88],"abrupt.":[91],"achieve":[93],"this":[94],"using":[96],"dynamic":[98],"Dirichlet":[99],"prior":[100],"takes":[102],"into":[103],"account":[104],"data":[105],"contributions":[106],"other":[108],"topics.":[109],"BeamSeg":[110],"also":[111],"segment":[113],"length":[114],"properties":[115],"based":[118],"on":[119],"modality":[120],"(textbooks,":[121],"slides,":[122],"etc.).":[123],"evaluation":[125],"is":[126],"carried":[127],"out":[128],"three":[130],"datasets.":[131],"In":[132],"two":[133],"them,":[135],"improvements":[136],"up":[138],"4.8%":[140],"7.3%":[142],"obtained":[144],"identifications":[150],"tasks,":[151],"indicating":[152],"both":[154],"tasks":[155],"should":[156],"jointly":[158],"modeled.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}