{"id":"https://openalex.org/W7097288355","doi":null,"title":"2010b. Profiting from mark-up: Hyper-text annotations for guided parsing","display_name":"2010b. Profiting from mark-up: Hyper-text annotations for guided parsing","publication_year":2013,"publication_date":"2013-07-16","ids":{"openalex":"https://openalex.org/W7097288355"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.3758","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.3758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"http://aclweb.org/anthology/P/P10/P10-1130.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081436122","display_name":"Valentin I. Spitkovsky","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valentin I. Spitkovsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029769372","display_name":"Hiyan Alshawi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiyan Alshawi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Google Inc","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Google Inc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036266399","display_name":"Daniel S. Jurafsky","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Jurafsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51727447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"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"}},"topics":[{"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/html-tags","display_name":"HTML tags","score":0.8679999709129333},{"id":"https://openalex.org/keywords/grammatical-inference","display_name":"grammatical inference","score":0.9169999957084656},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.8420000076293945},{"id":"https://openalex.org/keywords/blog-corpus","display_name":"blog corpus","score":0.4259999990463257},{"id":"https://openalex.org/keywords/wall-street-journal-corpus","display_name":"Wall Street Journal corpus","score":0.5879999995231628},{"id":"https://openalex.org/keywords/brown-corpus","display_name":"Brown Corpus","score":0.777999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839999794960022},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7788000106811523},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7412999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633999943733215},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.6510999798774719},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C80877019","wikidata":"https://www.wikidata.org/wiki/Q7188074","display_name":"Phrase structure rules","level":3,"score":0.4108000099658966},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.3582000136375427},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.3758","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.3758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"http://aclweb.org/anthology/P/P10/P10-1130.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7003939747810364,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2107419438","https://openalex.org/W183201499","https://openalex.org/W7099305962","https://openalex.org/W64928986","https://openalex.org/W7099286888","https://openalex.org/W7096268584","https://openalex.org/W7097904198","https://openalex.org/W1584789421","https://openalex.org/W7096359747","https://openalex.org/W7095926861"],"abstract_inverted_index":{"We":[0,53],"show":[1,100],"how":[2],"web":[3,151],"mark-up":[4,152],"can":[5],"be":[6],"used":[7],"to":[8,33,89,129],"improve":[9],"unsupervised":[10],"dependency":[11],"parsing.":[12],"Starting":[13],"from":[14,112],"raw":[15],"bracketings":[16],"of":[17,42,46,82,114],"four":[18],"common":[19],"HTML":[20],"tags":[21],"(anchors,":[22],"bold,":[23],"italics":[24],"and":[25,64],"underlines),":[26],"we":[27],"refine":[28],"approximate":[29],"partial":[30],"phrase":[31],"boundaries":[32],"yield":[34],"accurate":[35],"parsing":[36,75],"constraints.":[37],"Conversion":[38],"procedures":[39],"fall":[40],"out":[41],"our":[43],"linguistic":[44],"analysis":[45],"a":[47,125],"newly":[48],"available":[49],"million-word":[50],"hyper-text":[51],"corpus.":[52],"demonstrate":[54],"that":[55,101,150],"derived":[56],"constraints":[57],"aid":[58],"grammar":[59],"induction":[60],"by":[61,94],"training":[62],"Klein":[63],"Manning\u2019s":[65],"Dependency":[66],"Model":[67],"with":[68,155],"Valence":[69],"(DMV)":[70],"on":[71,77,124],"this":[72],"data":[73],"set:":[74],"accuracy":[76,132],"Section":[78],"23":[79],"(all":[80],"sentences)":[81],"the":[83,102,135,144],"Wall":[84],"Street":[85],"Journal":[86],"corpus":[87,137],"jumps":[88],"50.4%,":[90],"beating":[91],"previous":[92,145],"state-of-theart":[93],"more":[95,116],"than":[96,143],"5%.":[97],"Web-scale":[98],"experiments":[99],"DMV,":[103],"perhaps":[104],"because":[105],"it":[106],"is":[107],"unlexicalized,":[108],"does":[109],"not":[110],"benefit":[111],"orders":[113],"magnitude":[115],"annotated":[117],"but":[118],"noisier":[119],"data.":[120],"Our":[121],"model,":[122],"trained":[123],"single":[126],"blog,":[127],"generalizes":[128],"53.3":[130],"%":[131,141],"out-of-domain,":[133],"against":[134],"Brown":[136],"\u2014":[138],"nearly":[139],"10":[140],"higher":[142],"published":[146],"best.":[147],"The":[148],"fact":[149],"strongly":[153],"correlates":[154],"syntactic":[156],"structure":[157],"may":[158],"have":[159],"broad":[160],"applicability":[161],"in":[162],"NLP.":[163],"1":[164]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}