{"id":"https://openalex.org/W2250288169","doi":"https://doi.org/10.18653/v1/d15-1148","title":"Detecting Content-Heavy Sentences: A Cross-Language Case Study","display_name":"Detecting Content-Heavy Sentences: A Cross-Language Case Study","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250288169","doi":"https://doi.org/10.18653/v1/d15-1148","mag":"2250288169"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1148","pdf_url":"https://www.aclweb.org/anthology/D15-1148.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 2015 Conference on Empirical Methods in Natural Language Processing","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/D15-1148.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021057186","display_name":"Junyi Jessy Li","orcid":"https://orcid.org/0000-0002-2550-5262"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyi Jessy Li","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"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/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ani Nenkova","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1271","last_page":"1281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","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/T13629","display_name":"Text Readability and Simplification","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":0.9993000030517578,"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":0.9991999864578247,"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":0.8143070936203003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7794983983039856},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.739829421043396},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.7336894869804382},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6531100273132324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6206573247909546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5570263266563416},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5342328548431396},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5132989287376404},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.44759634137153625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3734765350818634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143070936203003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7794983983039856},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.739829421043396},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7336894869804382},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6531100273132324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6206573247909546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5570263266563416},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5342328548431396},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5132989287376404},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.44759634137153625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3734765350818634},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1148","pdf_url":"https://www.aclweb.org/anthology/D15-1148.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.9064","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.9064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1148.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1148","pdf_url":"https://www.aclweb.org/anthology/D15-1148.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250288169.pdf","grobid_xml":"https://content.openalex.org/works/W2250288169.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1496518036","https://openalex.org/W1544285860","https://openalex.org/W1965314436","https://openalex.org/W2001064229","https://openalex.org/W2009856297","https://openalex.org/W2010812227","https://openalex.org/W2025617415","https://openalex.org/W2042262613","https://openalex.org/W2045320784","https://openalex.org/W2063490579","https://openalex.org/W2068537423","https://openalex.org/W2075179010","https://openalex.org/W2095751497","https://openalex.org/W2096204319","https://openalex.org/W2108373063","https://openalex.org/W2109802560","https://openalex.org/W2112282043","https://openalex.org/W2119954850","https://openalex.org/W2123442489","https://openalex.org/W2131296021","https://openalex.org/W2139079654","https://openalex.org/W2143995218","https://openalex.org/W2146113428","https://openalex.org/W2156422881","https://openalex.org/W2158217454","https://openalex.org/W2161996854","https://openalex.org/W2250531756","https://openalex.org/W2250929115","https://openalex.org/W2251074483","https://openalex.org/W2251831371","https://openalex.org/W2252267750","https://openalex.org/W2261586594","https://openalex.org/W2352162662","https://openalex.org/W2402998908","https://openalex.org/W2523717353","https://openalex.org/W2786305482","https://openalex.org/W2786536200","https://openalex.org/W3023740747"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W4300537970"],"abstract_inverted_index":{"The":[0],"information":[1],"conveyed":[2],"by":[3,11],"some":[4],"sentences":[5,24,47,57,102,139],"would":[6,64],"be":[7],"more":[8,69],"easily":[9],"understood":[10],"a":[12,142],"reader":[13,86],"if":[14],"it":[15],"were":[16],"expressed":[17],"in":[18,48,58,118,129],"multiple":[19,82],"sentences.":[20,36,150],"We":[21,73,92,121],"call":[22],"such":[23],"content":[25,100],"heavy:":[26],"these":[27,149],"are":[28,115,131],"possibly":[29],"grammatical":[30],"but":[31],"difficult":[32],"to":[33,55],"comprehend,":[34],"cumbersome":[35],"In":[37],"this":[38,111],"paper":[39],"we":[40,52],"introduce":[41],"the":[42],"task":[43],"of":[44,68,113],"detecting":[45,137],"content-heavy":[46],"cross-lingual":[49],"context.":[50],"Specifically":[51],"develop":[53],"methods":[54],"identify":[56],"Chinese":[59,119,130],"for":[60,135],"which":[61],"English":[62],"speakers":[63],"prefer":[65],"translations":[66,84],"consisting":[67],"than":[70,106],"one":[71],"sentence.":[72],"base":[74],"our":[75],"analysis":[76],"and":[77,85,90,109,126,140],"definitions":[78],"on":[79,88],"evidence":[80],"from":[81],"human":[83],"preferences":[87],"flow":[89],"understandability.":[91],"show":[93],"that":[94,110,123,146],"machine":[95],"translation":[96],"quality":[97,108],"when":[98],"translating":[99],"heavy":[101,138],"is":[103],"markedly":[104],"worse":[105],"overall":[107],"type":[112],"sentence":[114,124],"fairly":[116],"common":[117],"news.":[120],"demonstrate":[122],"length":[125],"punctuation":[127],"usage":[128],"not":[132],"sufficient":[133],"clues":[134],"accurately":[136,147],"present":[141],"richer":[143],"classification":[144],"model":[145],"identifies":[148]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}