{"id":"https://openalex.org/W183201499","doi":null,"title":"Punctuation: Making a Point in Unsupervised Dependency Parsing","display_name":"Punctuation: Making a Point in Unsupervised Dependency Parsing","publication_year":2011,"publication_date":"2011-06-23","ids":{"openalex":"https://openalex.org/W183201499","mag":"183201499"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5218","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5218","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-new/W/W11/W11-0303.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valentin I. Spitkovsky","raw_affiliation_strings":["Stanford University and Google, Inc.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University and Google, Inc.#TAB#","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029769372","display_name":"Hiyan Alshawi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hiyan Alshawi","raw_affiliation_strings":["Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036266399","display_name":"Daniel S. Jurafsky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Jurafsky","raw_affiliation_strings":["Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2943,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96065299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/punctuation","display_name":"punctuation","score":0.8560000061988831},{"id":"https://openalex.org/keywords/grammatical-inference","display_name":"grammatical inference","score":0.9169999957084656},{"id":"https://openalex.org/keywords/phrase-boundaries","display_name":"phrase boundaries","score":0.7630000114440918},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6980000138282776},{"id":"https://openalex.org/keywords/multilingual-parsing","display_name":"multilingual parsing","score":0.546999990940094},{"id":"https://openalex.org/keywords/wall-street-journal","display_name":"Wall Street Journal","score":0.49900001287460327},{"id":"https://openalex.org/keywords/penn-treebank","display_name":"Penn Treebank","score":0.7289999723434448}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9223353862762451},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9213193655014038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634257078170776},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.7411457300186157},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7024654150009155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6948270797729492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6671389937400818},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.6042571067810059},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5019619464874268},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5005302429199219},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4272664785385132},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3200272023677826},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.26061195135116577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5218","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5218","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-new/W/W11/W11-0303.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.6875","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.6875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/%7Evals/pubs/punctuation.pdf","raw_type":"text"},{"id":"mag:183201499","doi":null,"is_oa":false,"landing_page_url":"https://ai.google/research/pubs/pub37113.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":"Conference on Computational Natural Language Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W73274768","https://openalex.org/W97972967","https://openalex.org/W1495446613","https://openalex.org/W1530801890","https://openalex.org/W1535015163","https://openalex.org/W1544916875","https://openalex.org/W1551104980","https://openalex.org/W1568793342","https://openalex.org/W1577509415","https://openalex.org/W1632114991","https://openalex.org/W1781547478","https://openalex.org/W1848000237","https://openalex.org/W1909733559","https://openalex.org/W1964823536","https://openalex.org/W1984764846","https://openalex.org/W1986543644","https://openalex.org/W2010576059","https://openalex.org/W2018130343","https://openalex.org/W2027582570","https://openalex.org/W2027979924","https://openalex.org/W2039117335","https://openalex.org/W2041350511","https://openalex.org/W2056894934","https://openalex.org/W2060711947","https://openalex.org/W2067030274","https://openalex.org/W2087309226","https://openalex.org/W2088672056","https://openalex.org/W2092654472","https://openalex.org/W2096466920","https://openalex.org/W2107419438","https://openalex.org/W2107943277","https://openalex.org/W2111500764","https://openalex.org/W2113851376","https://openalex.org/W2115803233","https://openalex.org/W2117729721","https://openalex.org/W2134307360","https://openalex.org/W2135799088","https://openalex.org/W2139090905","https://openalex.org/W2141732516","https://openalex.org/W2153568660","https://openalex.org/W2153813398","https://openalex.org/W2153895584","https://openalex.org/W2157898978","https://openalex.org/W2160424800","https://openalex.org/W2166116787","https://openalex.org/W2169187092","https://openalex.org/W2293063786","https://openalex.org/W2294835092","https://openalex.org/W2398009384","https://openalex.org/W2398127254","https://openalex.org/W2439178139","https://openalex.org/W2569308312","https://openalex.org/W3023740747","https://openalex.org/W3088033278","https://openalex.org/W3089319657"],"related_works":["https://openalex.org/W64928986","https://openalex.org/W1527783480","https://openalex.org/W2890708025","https://openalex.org/W7099305962","https://openalex.org/W7095926861","https://openalex.org/W2180373279","https://openalex.org/W1848000237","https://openalex.org/W2136123081","https://openalex.org/W2107419438","https://openalex.org/W2252238553"],"abstract_inverted_index":{"We":[0],"show":[1],"how":[2],"punctuation":[3,21,34,63,114],"can":[4],"be":[5],"used":[6],"to":[7],"improve":[8],"unsupervised":[9],"dependency":[10],"parsing.":[11],"Our":[12,71],"linguistic":[13],"analysis":[14],"confirms":[15],"the":[16,26,37,77,101,108],"strong":[17],"connection":[18],"between":[19],"English":[20],"and":[22,50,64,82,159],"phrase":[23],"boundaries":[24],"in":[25,36,118,148,163],"Penn":[27],"Treebank.":[28],"However,":[29],"approaches":[30],"that":[31,113],"naively":[32],"include":[33],"marks":[35],"grammar":[38,72,116],"(as":[39],"if":[40],"they":[41],"were":[42],"words)":[43],"do":[44],"not":[45],"perform":[46],"well":[47],"with":[48,54,90,145,153],"Klein":[49],"Manning\u2019s":[51],"Dependency":[52],"Model":[53],"Valence":[55],"(DMV).":[56],"Instead,":[57],"we":[58],"split":[59],"a":[60],"sentence":[61],"at":[62],"impose":[65],"parsing":[66,144,157],"restrictions":[67],"over":[68],"its":[69],"fragments.":[70],"inducer":[73],"is":[74,135,142],"trained":[75],"on":[76],"Wall":[78],"Street":[79],"Journal":[80],"(WSJ)":[81],"achieves":[83],"59.5":[84],"%":[85,98],"accuracy":[86,162],"out-of-domain":[87],"(Brown":[88],"sentences":[89],"100":[91],"or":[92],"fewer":[93],"words),":[94],"more":[95,139],"than":[96,100,140],"6":[97],"higher":[99],"previous":[102],"best":[103],"results.":[104],"Further":[105],"evaluation,":[106],"using":[107],"2006/7":[109],"CoNLL":[110],"sets,":[111],"reveals":[112],"aids":[115],"induction":[117],"17":[119],"of":[120,129,132],"18":[121],"languages,":[122],"for":[123],"an":[124],"overall":[125],"average":[126],"net":[127],"gain":[128],"1.3%.":[130],"Some":[131],"this":[133],"improvement":[134],"from":[136,143],"training,":[137],"but":[138],"half":[141],"induced":[146],"constraints,":[147],"inference.":[149],"Punctuation-aware":[150],"decoding":[151],"works":[152],"existing":[154],"(even":[155],"already-trained)":[156],"models":[158],"always":[160],"increased":[161],"our":[164],"experiments.":[165],"1":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}