{"id":"https://openalex.org/W2072350158","doi":"https://doi.org/10.1109/icis.2014.6912128","title":"Exploiting limited data for parsing","display_name":"Exploiting limited data for parsing","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2072350158","doi":"https://doi.org/10.1109/icis.2014.6912128","mag":"2072350158"},"language":"en","primary_location":{"id":"doi:10.1109/icis.2014.6912128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2014.6912128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/ACIS 13th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5077077784","display_name":"Dongchen Li","orcid":"https://orcid.org/0000-0001-8126-0805"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongchen Li","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Beijing, China","Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062995314","display_name":"Xiantao Zhang","orcid":"https://orcid.org/0000-0002-3795-3556"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantao Zhang","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Beijing, China","Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Beijing, China","Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Laboratory of Machine Perception and Intelligence, Speech and Hearing Research Center, School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077077784"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09683207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"171","last_page":"175"},"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":0.9998000264167786,"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":"Text Readability and Simplification","score":0.9811999797821045,"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":0.8514426946640015},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7066635489463806},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.6598870754241943},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6416262984275818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5969313979148865},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.4712942838668823},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4673942029476166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4169135093688965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3880562484264374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514426946640015},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7066635489463806},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.6598870754241943},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6416262984275818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5969313979148865},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.4712942838668823},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4673942029476166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4169135093688965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3880562484264374},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icis.2014.6912128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icis.2014.6912128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/ACIS 13th International Conference on Computer and Information Science (ICIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W116210019","https://openalex.org/W1535015163","https://openalex.org/W1781980207","https://openalex.org/W1894695003","https://openalex.org/W1982649163","https://openalex.org/W1983728325","https://openalex.org/W2042168563","https://openalex.org/W2067323260","https://openalex.org/W2079182758","https://openalex.org/W2092654472","https://openalex.org/W2097606805","https://openalex.org/W2111536437","https://openalex.org/W2113691817","https://openalex.org/W2116064496","https://openalex.org/W2118584553","https://openalex.org/W2125712079","https://openalex.org/W2128092251","https://openalex.org/W2132726600","https://openalex.org/W2134729743","https://openalex.org/W2139621418","https://openalex.org/W2146113428","https://openalex.org/W2161204834","https://openalex.org/W2163568299","https://openalex.org/W2425667873","https://openalex.org/W2788296320","https://openalex.org/W2949524199","https://openalex.org/W3021452258","https://openalex.org/W6604743809","https://openalex.org/W6632145054","https://openalex.org/W6638089094","https://openalex.org/W6639914256","https://openalex.org/W6673531037","https://openalex.org/W6676777077","https://openalex.org/W6677996398","https://openalex.org/W6679897855","https://openalex.org/W6680008805","https://openalex.org/W6680385414","https://openalex.org/W6683676627","https://openalex.org/W7075629402"],"related_works":["https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W2109902858","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2575884139","https://openalex.org/W2017946383"],"abstract_inverted_index":{"Data":[0],"sparsity":[1,199],"issues":[2],"are":[3,24,129],"extremely":[4],"severe":[5],"for":[6,26],"parser":[7],"due":[8],"to":[9,83,89,193,195],"the":[10,27,59,101,108,145],"flexibility":[11],"of":[12,61,111],"tree":[13,113],"structures.":[14],"Many":[15],"tags":[16],"and":[17,79,121,152,185],"productions":[18],"appears":[19],"a":[20,35,42,55,70,141,157],"little,":[21],"nevertheless,":[22],"they":[23],"crucial":[25],"parse":[28],"disambiguation":[29],"where":[30],"it":[31],"occurs.":[32],"Besides,":[33],"when":[34,94],"common":[36],"tag":[37],"somewhat":[38],"regularly":[39],"occurs":[40],"in":[41,87,116,156,200],"non-canonical":[43],"position,":[44],"its":[45,161],"distribution":[46],"is":[47,191],"usually":[48],"distinct.":[49],"In":[50],"this":[51,136,189],"paper,":[52],"we":[53,81,138],"propose":[54,140],"metric":[56],"that":[57,143],"measures":[58],"scarcity":[60],"any":[62],"phrase":[63],"with":[64,76,181,197],"arbitrary":[65],"span":[66],"size.":[67],"To":[68],"make":[69],"better":[71],"compromise":[72],"between":[73],"training":[74,95,147,163],"trees":[75],"high":[77],"confidence":[78],"scarcity,":[80],"try":[82],"catch":[84],"some":[85,179],"constraints":[86],"response":[88],"rare":[90],"but":[91],"articulating":[92],"categories":[93],"latent":[96],"variable":[97],"grammar.":[98],"We":[99],"exploits":[100,144],"limited":[102,146,162],"data":[103,184,198],"more":[104],"sufficiently":[105],"by":[106],"capturing":[107],"depicting":[109],"power":[110],"rate":[112],"structure":[114],"configuration":[115],"Expectation":[117],"&":[118,123],"Maximization":[119],"procedure":[120],"Split":[122],"Merge":[124],"framework.":[125],"The":[126],"resulting":[127],"grammars":[128],"interpretable":[130],"as":[131],"our":[132],"intension.":[133],"Based":[134],"on":[135,170],"approach,":[137],"further":[139],"method":[142,190],"date":[148],"from":[149],"multiple":[150],"perspectives,":[151],"accumulates":[153],"their":[154],"advantages":[155],"product":[158],"model.":[159],"Despite":[160],"data,":[164],"out":[165],"model":[166],"improves":[167],"parsing":[168],"performance":[169],"Penn":[171],"Chinese":[172],"Treebank":[173],"Fifth":[174],"Edition,":[175],"even":[176],"higher":[177],"than":[178],"systems":[180],"extra":[182],"unlabeled":[183],"external":[186],"resources.":[187],"Furthermore,":[188],"easy":[192],"generalized":[194],"cope":[196],"other":[201],"natural":[202],"language":[203],"processing":[204],"tasks.":[205]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}