{"id":"https://openalex.org/W2250255835","doi":"https://doi.org/10.3115/v1/w14-0801","title":"Breaking Bad: Extraction of Verb-Particle Constructions from a Parallel Subtitles Corpus","display_name":"Breaking Bad: Extraction of Verb-Particle Constructions from a Parallel Subtitles Corpus","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250255835","doi":"https://doi.org/10.3115/v1/w14-0801","mag":"2250255835"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0801","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0801","pdf_url":null,"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 Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w14-0801","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aaron Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Aaron Smith","raw_affiliation_strings":["Uppsala University, Uppsala, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17174598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T13629","display_name":"Text Readability and Simplification","score":0.9944999814033508,"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":0.9799000024795532,"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":0.8354567289352417},{"id":"https://openalex.org/keywords/slang","display_name":"Slang","score":0.6703029870986938},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.6591836214065552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6591037511825562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5877326130867004},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5860664248466492},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5181997418403625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3693379759788513},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18636101484298706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354567289352417},{"id":"https://openalex.org/C2779901982","wikidata":"https://www.wikidata.org/wiki/Q8102","display_name":"Slang","level":2,"score":0.6703029870986938},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.6591836214065552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6591037511825562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877326130867004},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5860664248466492},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5181997418403625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3693379759788513},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18636101484298706},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-0801","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0801","pdf_url":null,"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 Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.666","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/W/W14/W14-0801.pdf","raw_type":"text"},{"id":"mag:2250255835","is_oa":false,"landing_page_url":"https://uu.diva-portal.org/smash/record.jsf?pid=diva2:905864","pdf_url":null,"source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Conference of the European Chapter of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":{"id":"doi:10.3115/v1/w14-0801","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0801","pdf_url":null,"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 Workshop on Multiword Expressions (MWE)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2576981735","https://openalex.org/W1580452537","https://openalex.org/W2383860274","https://openalex.org/W1576928919","https://openalex.org/W2524010971","https://openalex.org/W2752697875","https://openalex.org/W2398127254","https://openalex.org/W2464775082","https://openalex.org/W2757753881","https://openalex.org/W2574026469","https://openalex.org/W2071883824","https://openalex.org/W361910221","https://openalex.org/W1982840093","https://openalex.org/W2191068822","https://openalex.org/W2131526336","https://openalex.org/W1999281650","https://openalex.org/W3211403070","https://openalex.org/W2584080049","https://openalex.org/W125496762","https://openalex.org/W2026908487"],"abstract_inverted_index":{"The":[0],"automatic":[1],"extraction":[2],"of":[3,8,34,49,53,56,58,81,96,103,111,125,136,145,164,172,188,205],"verb-particle":[4],"constructions":[5],"(VPCs)":[6],"is":[7,43,64,75,98,151,167],"particular":[9],"inter-est":[10],"to":[11,29,45,192],"the":[12,41,101,112,123,147,170,189],"NLP":[13],"community.":[14],"Previous":[15],"stud-ies":[16],"have":[17],"shown":[18,76],"that":[19,77,152,181,199,208],"word":[20,148,195],"alignment":[21,149,196],"meth-ods":[22],"can":[23,86],"be":[24,87],"used":[25],"with":[26],"parallel":[27],"corpora":[28],"successfully":[30],"extract":[31],"a":[32,46,54,78,133,184,203],"range":[33,204],"multi-word":[35],"expressions":[36,207],"(MWEs).":[37],"In":[38],"this":[39,127],"paper":[40],"technique":[42],"applied":[44],"new":[47],"type":[48],"cor-pus,":[50],"made":[51],"up":[52],"collection":[55],"subtitles":[57,107,200],"movies":[59],"and":[60,68,105,138,198],"television":[61],"series,":[62],"which":[63,131],"par-allel":[65],"in":[66,89,118,212],"English":[67,90,173],"Spanish.":[69,176],"Building":[70],"on":[71],"previous":[72],"research,":[73],"it":[74],"preci-sion":[79],"level":[80,95],"94":[82],"\u00b1":[83],"4.7":[84],"%":[85,166],"achieved":[88,99],"VPC":[91],"extraction.":[92],"This":[93,177],"high":[94],"precision":[97,162],"despite":[100],"dif-ficulties":[102],"aligning":[104],"tagging":[106],"data.":[108],"Moreover,":[109],"many":[110],"extracted":[113,157],"VPCs":[114,174,182],"are":[115,154,183],"not":[116,210],"present":[117],"online":[119],"lexical":[120],"re-sources,":[121],"highlighting":[122],"benefits":[124],"using":[126,146,194],"unique":[128],"corpus":[129,214],"type,":[130],"contains":[132],"large":[134],"number":[135],"slang":[137],"other":[139,213],"informal":[140],"expressions.":[141],"An":[142],"added":[143],"benefit":[144],"process":[150],"trans-lations":[153],"also":[155],"automatically":[156],"for":[158,169],"each":[159],"VPC.":[160],"A":[161],"rate":[163],"75\u00b18.5":[165],"found":[168],"translations":[171],"into":[175],"study":[178],"thus":[179],"shows":[180],"particularly":[185],"good":[186],"subset":[187],"MWE":[190],"spectrum":[191],"attack":[193],"methods,":[197],"data":[201],"provide":[202],"interesting":[206],"do":[209],"exist":[211],"types.":[215],"1":[216]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}