{"id":"https://openalex.org/W2170869176","doi":"https://doi.org/10.1162/089120105775299140","title":"Induction of Word and Phrase Alignments for Automatic Document Summarization","display_name":"Induction of Word and Phrase Alignments for Automatic Document Summarization","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W2170869176","doi":"https://doi.org/10.1162/089120105775299140","mag":"2170869176"},"language":"en","primary_location":{"id":"doi:10.1162/089120105775299140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299140","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":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299140","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019928111","display_name":"Hal Daum\u00e9","orcid":"https://orcid.org/0000-0002-3760-345X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hal Daum\u00e9","raw_affiliation_strings":["Information Sciences Institute University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005020376","display_name":"Daniel Marcu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Marcu","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005020376","https://openalex.org/A5019928111"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":4.5943,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.947725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":"4","first_page":"505","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.992900013923645,"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":0.9023399353027344},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8709577918052673},{"id":"https://openalex.org/keywords/headline","display_name":"Headline","score":0.7925205230712891},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7392314672470093},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6688703298568726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6555147767066956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6499015688896179},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5871603488922119},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4825291335582733},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4602040946483612},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4492088258266449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.393830269575119},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08584651350975037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9023399353027344},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8709577918052673},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.7925205230712891},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7392314672470093},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6688703298568726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6555147767066956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6499015688896179},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5871603488922119},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4825291335582733},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4602040946483612},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4492088258266449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.393830269575119},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08584651350975037},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":6,"locations":[{"id":"doi:10.1162/089120105775299140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299140","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:CiteSeerX.psu:10.1.1.207.1956","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.1956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal3.name/docs/daume05alignments.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.314.2134","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.314.2134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/0907.0804v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.7747","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.7747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology-new/J/J05/J05-4004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.3586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.3586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/~marcu/papers/daume05alignments.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:ff2e1176ffa440a7bf27bbc878b9c0f7","is_oa":false,"landing_page_url":"https://doaj.org/article/ff2e1176ffa440a7bf27bbc878b9c0f7","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 31, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120105775299140","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120105775299140","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120105775299140","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","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G3673068085","display_name":"A Maximum Entropy-Based Approach to Discourse Parsing","funder_award_id":"0097846","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170869176.pdf","grobid_xml":"https://content.openalex.org/works/W2170869176.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W99221312","https://openalex.org/W157686461","https://openalex.org/W174630521","https://openalex.org/W317397600","https://openalex.org/W1544729927","https://openalex.org/W1567570606","https://openalex.org/W1577877742","https://openalex.org/W1597655096","https://openalex.org/W1964326564","https://openalex.org/W1973923101","https://openalex.org/W1974339500","https://openalex.org/W1976551160","https://openalex.org/W1996333538","https://openalex.org/W1998369932","https://openalex.org/W2006969979","https://openalex.org/W2007321142","https://openalex.org/W2028339364","https://openalex.org/W2038698865","https://openalex.org/W2042262613","https://openalex.org/W2048305092","https://openalex.org/W2049633694","https://openalex.org/W2053742104","https://openalex.org/W2061235289","https://openalex.org/W2077574412","https://openalex.org/W2083393647","https://openalex.org/W2100969003","https://openalex.org/W2101390659","https://openalex.org/W2103164118","https://openalex.org/W2115167129","https://openalex.org/W2116316001","https://openalex.org/W2118686841","https://openalex.org/W2133182690","https://openalex.org/W2143008661","https://openalex.org/W2144637381","https://openalex.org/W2147496287","https://openalex.org/W2153804780","https://openalex.org/W2156985047","https://openalex.org/W2163205257","https://openalex.org/W2166347079","https://openalex.org/W2270719270","https://openalex.org/W3035219831","https://openalex.org/W3129711340","https://openalex.org/W3150541299","https://openalex.org/W3151369355","https://openalex.org/W4205167092","https://openalex.org/W4231741839"],"related_works":["https://openalex.org/W4285135530","https://openalex.org/W2380567098","https://openalex.org/W2035489689","https://openalex.org/W906669285","https://openalex.org/W1553197492","https://openalex.org/W85886512","https://openalex.org/W1586468330","https://openalex.org/W1514610457","https://openalex.org/W3173716828","https://openalex.org/W3198337106"],"abstract_inverted_index":{"Current":[0],"research":[1],"in":[2,26,87,151,221,230,252],"automatic":[3,88],"single-document":[4],"summarization":[5,14,89,165],"is":[6,33,61,205,241],"dominated":[7],"by":[8,15,45,94],"two":[9],"effective,":[10],"yet":[11],"na\u00efve":[12],"approaches:":[13],"sentence":[16],"extraction":[17],"and":[18,78,134,139,155,187,216,232,249],"headline":[19,80],"generation":[20],"via":[21],"bagof-words":[22],"models.":[23],"While":[24],"successful":[25],"some":[27],"tasks,":[28],"neither":[29],"of":[30,41,58,97,110,123,181,210,255],"these":[31,59,124,190],"models":[32,60],"able":[34,242],"to":[35,68,115,119,177,183,218,243,245],"adequately":[36],"capture":[37],"the":[38,55,95,117,147,179,202,211],"large":[39],"set":[40],"linguistic":[42],"devices":[43],"utilized":[44],"humans":[46,182],"when":[47],"they":[48],"produce":[49],"summaries.":[50],"One":[51],"possible":[52],"explanation":[53],"for":[54,73,130,195,201],"widespread":[56],"use":[57],"that":[62,84,149,236,238],"good":[63],"techniques":[64,129],"have":[65,127,174],"been":[66],"developed":[67,128],"extract":[69],"appropriate":[70],"training":[71],"data":[72,160],"them":[74,197],"from":[75,162],"existing":[76],"document/abstract":[77,111,153],"document/":[79],"corpora.":[81,112],"We":[82,226],"believe":[83],"future":[85],"progress":[86],"will":[90],"be":[91],"driven":[92],"both":[93,122],"development":[96],"more":[98,107],"sophisticated,":[99],"linguistically":[100],"informed":[101],"models,":[102],"as":[103,105],"well":[104],"a":[106,157,222,253],"effective":[108],"leveraging":[109],"In":[113],"order":[114],"open":[116],"doors":[118],"simultaneously":[120],"achieving":[121],"goals,":[125],"we":[126,173,192],"automatically":[131],"producing":[132],"word-to-word":[133],"phrase-to-phrase":[135],"alignments":[136,144,220,251],"between":[137],"documents":[138],"their":[140],"human-written":[141],"abstracts.":[142],"These":[143],"make":[145],"explicit":[146],"correspondences":[148],"exist":[150],"such":[152,185],"pairs":[154],"create":[156,219],"potentially":[158],"rich":[159],"source":[161],"which":[163],"complex":[164],"algorithms":[166],"may":[167],"learn.":[168],"This":[169],"paper":[170],"describes":[171],"experiments":[172,194],"carried":[175],"out":[176],"analyze":[178],"ability":[180],"perform":[184],"alignments,":[186],"based":[188,206],"on":[189,207],"analyses,":[191],"describe":[193,227],"creating":[196],"automatically.":[198],"Our":[199],"model":[200,215,229,240],"alignment":[203],"task":[204],"an":[208],"extension":[209],"standard":[212],"hidden":[213],"Markov":[214],"learns":[217],"completely":[223],"unsupervised":[224],"fashion.":[225],"our":[228,239],"detail":[231],"present":[233],"experimental":[234],"results":[235],"show":[237],"learn":[244],"reliably":[246],"identify":[247],"word-":[248],"phrase-level":[250],"corpus":[254],"(document,":[256],"abstract)":[257],"pairs.":[258]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}