{"id":"https://openalex.org/W2083360710","doi":"https://doi.org/10.1117/12.713355","title":"Statistically-constrained shallow text marking: techniques, evaluation paradigm and results","display_name":"Statistically-constrained shallow text marking: techniques, evaluation paradigm and results","publication_year":2007,"publication_date":"2007-02-26","ids":{"openalex":"https://openalex.org/W2083360710","doi":"https://doi.org/10.1117/12.713355","mag":"2083360710"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.713355","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.tara.tcd.ie/bitstream/2262/32209/1/Statistically-constrained.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029850297","display_name":"Brian Murphy","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Brian Murphy","raw_affiliation_string":"Trinity College Dublin,Ireland","raw_affiliation_strings":["Trinity College Dublin,Ireland"]},{"author_position":"last","author":{"id":"https://openalex.org/A5081875121","display_name":"Carl Vogel","orcid":"https://orcid.org/0000-0001-8928-8546"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Carl Vogel","raw_affiliation_string":"Trinity College Dublin,Ireland","raw_affiliation_strings":["Trinity College Dublin,Ireland"]}],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":13,"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Statistical Machine Translation and Natural Language Processing","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/T10181","display_name":"Statistical Machine Translation and Natural Language Processing","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/T10028","display_name":"Natural Language Processing","score":0.9998,"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":"Automatic Text Simplification and Readability Assessment","score":0.9993,"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":[{"keyword":"shallow text","score":0.6869},{"keyword":"statistically-constrained","score":0.25}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.71485865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.67184913},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.595722},{"id":"https://openalex.org/C2777683214","wikidata":"https://www.wikidata.org/wiki/Q34698","display_name":"Adjective","level":3,"score":0.5727578},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.56945705},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5369757},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.53414553},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48185003},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.44831046},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4450106},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41449052},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.38202256},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22565833},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15084815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13994882},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.713355","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/32209","pdf_url":"http://www.tara.tcd.ie/bitstream/2262/32209/1/Statistically-constrained.pdf","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":["Dublin Institute of Technology"],"type":"repository"},"license":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/32209","pdf_url":"http://www.tara.tcd.ie/bitstream/2262/32209/1/Statistically-constrained.pdf","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":["Dublin Institute of Technology"],"type":"repository"},"license":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","score":0.72,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1605292408","https://openalex.org/W1832326700","https://openalex.org/W1919975936","https://openalex.org/W2000399774","https://openalex.org/W2014516359","https://openalex.org/W2025994941","https://openalex.org/W2081687495","https://openalex.org/W2086677051","https://openalex.org/W2089798121","https://openalex.org/W2102381086","https://openalex.org/W2111592878","https://openalex.org/W2121435899","https://openalex.org/W2124416056","https://openalex.org/W2146170623","https://openalex.org/W2170381724","https://openalex.org/W2611565525","https://openalex.org/W2615724484"],"related_works":["https://openalex.org/W4312381793","https://openalex.org/W2976849154","https://openalex.org/W2385963184","https://openalex.org/W2350058787","https://openalex.org/W3139255945","https://openalex.org/W2902614234","https://openalex.org/W2068167831","https://openalex.org/W4388156376","https://openalex.org/W2745526283","https://openalex.org/W3112308623"],"ngrams_url":"https://api.openalex.org/works/W2083360710/ngrams","abstract_inverted_index":{"We":[0,29],"present":[1],"three":[2],"natural":[3],"language":[4],"marking":[5],"strategies":[6],"based":[7,89],"on":[8,16,33],"fast":[9],"and":[10,15,26,51,58,79,92,95],"reliable":[11],"shallow":[12],"parsing":[13],"techniques,":[14],"widely":[17],"available":[18],"lexical":[19,21,56],"resources:":[20],"substitution,":[22],"adjective":[23],"conjunction":[24],"swaps,":[25],"relativiser":[27],"switching.":[28],"test":[30],"these":[31],"techniques":[32],"a":[34,62,85],"random":[35],"sample":[36,66],"of":[37,49,67,81,122,144,152],"the":[38,59,149],"British":[39],"National":[40],"Corpus.":[41],"Individual":[42],"candidate":[43],"marks":[44,68],"are":[45],"checked":[46],"for":[47,77,118,157],"goodness":[48],"structural":[50],"semantic":[52],"fit,":[53],"using":[54],"both":[55],"resources,":[57],"web":[60],"as":[61],"corpus.":[63],"A":[64,127],"representative":[65],"is":[69,140],"given":[70],"to":[71,75,116,163],"25":[72],"human":[73,125],"judges":[74],"evaluate":[76],"acceptability":[78,100],"preservation":[80],"meaning.":[82],"This":[83],"establishes":[84],"correlation":[86,139],"between":[87],"corpus":[88],"felicity":[90],"measures":[91],"perceived":[93],"quality,":[94],"makes":[96],"qualified":[97],"predictions.":[98],"Grammatical":[99],"correlates":[101],"with":[102,142],"our":[103,158],"automatic":[104,159],"measure":[105,160],"strongly":[106],"(Pearson's":[107,132],"r":[108,133],"=":[109,112,134,137],"0.795,":[110],"p":[111,136],"0.001),":[113],"allowing":[114],"us":[115],"account":[117],"about":[119],"two":[120],"thirds":[121],"variability":[123],"in":[124],"judgements.":[126],"moderate":[128],"but":[129],"statistically":[130],"insignificant":[131],"0.422,":[135],"0.356)":[138],"found":[141],"judgements":[143],"meaning":[145],"preservation,":[146],"indicating":[147],"that":[148],"contextual":[150],"window":[151],"five":[153],"content":[154],"words":[155],"used":[156],"may":[161],"need":[162],"be":[164],"extended.":[165]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2083360710","counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2024-03-27T06:22:39.959132","created_date":"2016-06-24"}