{"id":"https://openalex.org/W2015172077","doi":"https://doi.org/10.1109/isda.2010.5687043","title":"Improving statistical parsing by linguistic regularization","display_name":"Improving statistical parsing by linguistic regularization","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2015172077","doi":"https://doi.org/10.1109/isda.2010.5687043","mag":"2015172077"},"language":"en","primary_location":{"id":"doi:10.1109/isda.2010.5687043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2010.5687043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th International Conference on Intelligent Systems Design and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/71163","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002659016","display_name":"Igor Malioutov","orcid":"https://orcid.org/0000-0002-4058-6638"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Igor Malioutov","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA\u00a002139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA\u00a002139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052077756","display_name":"Robert C. Berwick","orcid":"https://orcid.org/0000-0002-1061-1871"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert C. Berwick","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA\u00a002139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA\u00a002139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002659016"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09857504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"1071","last_page":"1076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9922999739646912,"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/parsing","display_name":"Parsing","score":0.8049913644790649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781627535820007},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6134412288665771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5650467872619629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595699548721313},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37258481979370117},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08729544281959534}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8049913644790649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781627535820007},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6134412288665771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5650467872619629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595699548721313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37258481979370117},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08729544281959534}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isda.2010.5687043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2010.5687043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th International Conference on Intelligent Systems Design and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/71163","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/71163","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/71163","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/71163","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W10376690","https://openalex.org/W1502614524","https://openalex.org/W1535183358","https://openalex.org/W1551104980","https://openalex.org/W1985754308","https://openalex.org/W2009720124","https://openalex.org/W2079326125","https://openalex.org/W2092654472","https://openalex.org/W2093647425","https://openalex.org/W2098967945","https://openalex.org/W2111780752","https://openalex.org/W2167072947","https://openalex.org/W2600110521","https://openalex.org/W6600441966","https://openalex.org/W6632973184","https://openalex.org/W6684344272"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W1502858101","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Statistically-based":[0],"parsers":[1],"for":[2,91,107],"large":[3],"corpora,":[4],"in":[5,21,35,133,156],"particular":[6],"the":[7,17,22,41,50,57,109,134,139,161],"Penn":[8],"Tree":[9],"Bank":[10],"(PTB),":[11],"typically":[12],"have":[13,33,119],"not":[14,34],"used":[15,37,84],"all":[16],"linguistic":[18],"information":[19,38,71,90],"encoded":[20],"annotated":[23],"trees":[24],"on":[25,131],"which":[26],"they":[27,32],"are":[28],"trained.":[29],"In":[30,95],"particular,":[31],"general":[36],"that":[39,81,137],"records":[40],"effects":[42],"of":[43,52,89,100,104,141,164],"derivations,":[44,74],"such":[45],"as":[46,55,85],"empty":[47],"categories":[48],"and":[49,62,112],"representation":[51],"displaced":[53],"phrases,":[54],"is":[56],"case":[58],"with":[59],"passive,":[60],"topicalization,":[61],"wh-constructions.":[63],"Here":[64],"we":[65,97,146],"explore":[66],"ways":[67],"to":[68,72,122],"use":[69,99,140],"this":[70,157],"\u201cunwind\u201d":[73],"yielding":[75],"a":[76,128],"regularized":[77],"underlying":[78,115],"syntactic":[79,144,166],"structure":[80,111,116],"can":[82,147],"be":[83],"an":[86],"additional":[87],"source":[88],"more":[92],"accurate":[93],"parsing.":[94],"effect,":[96],"make":[98],"two":[101,143],"joint":[102],"sets":[103],"tree":[105],"structures":[106],"parsing:":[108],"surface":[110],"its":[113],"corresponding":[114],"where":[117],"arguments":[118],"been":[120],"restored":[121],"their":[123],"canonical":[124],"positions.":[125],"We":[126],"present":[127],"pilot":[129],"experiment":[130],"passives":[132],"PTB":[135],"indicating":[136],"through":[138],"these":[142],"representations":[145],"improve":[148],"overall":[149],"parsing":[150],"performance":[151],"by":[152],"exploiting":[153],"transformational":[154],"regularities,":[155],"way":[158],"paring":[159],"down":[160],"search":[162],"space":[163],"possible":[165],"analyses.":[167]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}