{"id":"https://openalex.org/W2518165207","doi":"https://doi.org/10.18653/v1/w16-1717","title":"Phrase Generalization: a Corpus Study in Multi-Document Abstracts and Original News Alignments","display_name":"Phrase Generalization: a Corpus Study in Multi-Document Abstracts and Original News Alignments","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2518165207","doi":"https://doi.org/10.18653/v1/w16-1717","mag":"2518165207"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-1717","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1717","pdf_url":"https://www.aclweb.org/anthology/W16-1717.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 10th Linguistic Annotation Workshop held in\n          conjunction with ACL 2016 (LAW-X 2016)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-1717.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017509415","display_name":"Ariani Di Felippo","orcid":"https://orcid.org/0000-0002-4566-9352"},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ariani Di-Felippo","raw_affiliation_strings":["Federal University of So Carlos Language and Literature Dept. Rod. Washington Luis, km 235 (SP-310) So Carlos, SP 13565-905, Brazil","Federal University of S\u00e3o Carlos Language and Literature Dept. Rod. Washington Luis, km 235 (SP-310) S\u00e3o Carlos, SP 13565-905, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of So Carlos Language and Literature Dept. Rod. Washington Luis, km 235 (SP-310) So Carlos, SP 13565-905, Brazil","institution_ids":["https://openalex.org/I177909021"]},{"raw_affiliation_string":"Federal University of S\u00e3o Carlos Language and Literature Dept. Rod. Washington Luis, km 235 (SP-310) S\u00e3o Carlos, SP 13565-905, Brazil","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032571629","display_name":"Ani Nenkova","orcid":"https://orcid.org/0000-0002-5825-7875"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ani Nenkova","raw_affiliation_strings":["University of Pennsylvania Computer and Information Science Dept. 3330 Walnut St. Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania Computer and Information Science Dept. 3330 Walnut St. Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"151","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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":0.9966999888420105,"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/phrase","display_name":"Phrase","score":0.8072072267532349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890022993087769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7557936906814575},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6594370603561401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6581199169158936},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41325491666793823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3271157741546631},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08011999726295471}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8072072267532349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890022993087769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7557936906814575},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6594370603561401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6581199169158936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41325491666793823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3271157741546631},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08011999726295471},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-1717","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1717","pdf_url":"https://www.aclweb.org/anthology/W16-1717.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 10th Linguistic Annotation Workshop held in\n          conjunction with ACL 2016 (LAW-X 2016)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-1717","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-1717","pdf_url":"https://www.aclweb.org/anthology/W16-1717.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 10th Linguistic Annotation Workshop held in\n          conjunction with ACL 2016 (LAW-X 2016)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4402799499","display_name":null,"funder_award_id":"2015/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2518165207.pdf","grobid_xml":"https://content.openalex.org/works/W2518165207.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W41776650","https://openalex.org/W214139340","https://openalex.org/W1498416817","https://openalex.org/W1552023264","https://openalex.org/W1892833822","https://openalex.org/W2005603124","https://openalex.org/W2066972299","https://openalex.org/W2083451366","https://openalex.org/W2118119027","https://openalex.org/W2118681326","https://openalex.org/W2122311631","https://openalex.org/W2126526697","https://openalex.org/W2138556193","https://openalex.org/W2144719390","https://openalex.org/W2144933361","https://openalex.org/W2150869743","https://openalex.org/W2153476384","https://openalex.org/W2181651573","https://openalex.org/W2250818300","https://openalex.org/W2293771131"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W1630076647","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2060629350","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W2349302580"],"abstract_inverted_index":{"Content":[0],"can":[1],"be":[2],"expressed":[3],"at":[4,101,107],"different":[5],"levels":[6],"of":[7,12,41,60,64,133,152],"specificity,":[8],"varying":[9],"the":[10,16,39,58,102,116,136,145,150],"amount":[11],"detail":[13],"presented":[14],"to":[15,20,37,56],"reader.":[17],"The":[18,62,125],"need":[19,36],"transform":[21],"specific":[22,157],"content":[23,68],"into":[24],"more":[25,86,153,156],"general":[26,154],"form":[27],"naturally":[28],"arises":[29],"in":[30],"summarization,":[31],"where":[32],"people":[33],"and":[34,51,70,88,98,113,123],"machines":[35],"convey":[38],"gist":[40],"a":[42,81,85,108,141],"text":[43],"within":[44],"imposed":[45],"space":[46],"constraints.":[47],"Completely":[48],"removing":[49],"sentences":[50],"phrases":[52],"is":[53],"one":[54],"way":[55],"reduce":[57],"level":[59],"detail.":[61],"bulk":[63],"work":[65],"on":[66,84,95,128],"summarization":[67],"selection":[69],"compression":[71],"deal":[72],"with":[73],"these":[74],"tasks.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79,105],"present":[80],"corpus":[82],"study":[83],"subtle":[87],"understudied":[89],"phenomenon:":[90],"noun":[91],"phrase":[92,103],"generalization.":[93],"Based":[94],"multi-document":[96],"news":[97],"abstract":[99],"alignments":[100],"level,":[104],"arrive":[106],"five":[109],"category":[110,119],"classification":[111],"scheme":[112],"find":[114],"that":[115],"most":[117],"common":[118],"requires":[120],"semantic":[121],"interpretation":[122],"inference.":[124],"others":[126],"rely":[127],"lexical":[129],"substitution":[130],"or":[131,155],"deletion":[132],"details":[134],"from":[135],"original":[137],"expression.":[138],"We":[139],"provide":[140],"systematic":[142],"analysis,":[143],"elucidating":[144],"capabilities":[146],"needed":[147],"for":[148],"automating":[149],"generation":[151],"references.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}