{"id":"https://openalex.org/W2095955690","doi":"https://doi.org/10.3115/1073012.1073046","title":"XML-based data preparation for robust deep parsing","display_name":"XML-based data preparation for robust deep parsing","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2095955690","doi":"https://doi.org/10.3115/1073012.1073046","mag":"2095955690"},"language":"en","primary_location":{"id":"doi:10.3115/1073012.1073046","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073046","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073046","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108653041","display_name":"Claire Grover","orcid":"https://orcid.org/0000-0001-7019-1250"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Claire Grover","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, UK","\u00a7The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"\u00a7The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083233594","display_name":"Alex Lascarides","orcid":"https://orcid.org/0000-0003-1704-1864"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Lascarides","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, UK","\u00a7The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"\u00a7The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"260","last_page":"267"},"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":0.9987000226974487,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9948999881744385,"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":0.8984978199005127},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7884015440940857},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6396285891532898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5838152170181274},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5609778165817261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5106564164161682},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49157628417015076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4865962266921997},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4470939040184021},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4443504810333252},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.439360648393631},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.4277569055557251},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4248463213443756},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.35869038105010986},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.20849210023880005},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1692974865436554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8984978199005127},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7884015440940857},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6396285891532898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5838152170181274},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5609778165817261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5106564164161682},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49157628417015076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4865962266921997},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4470939040184021},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4443504810333252},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.439360648393631},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.4277569055557251},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4248463213443756},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.35869038105010986},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.20849210023880005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1692974865436554},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3115/1073012.1073046","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073046","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7807556e-1db9-486c-9bf6-ad570f039c20","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7807556e-1db9-486c-9bf6-ad570f039c20","pdf_url":"https://www.research.ed.ac.uk/files/18764799/Grover_Lascardies_2001_XML_Based_Data_Preparation_for_Robust_Deep_Parsing.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grover, C & Lascarides, A 2001, XML-Based Data Preparation for Robust Deep Parsing. in Association for Computational Linguistic, 39th Annual Meeting and 10th Conference of the European Chapter, Proceedings of the Conference, July 9-11, 2001, Toulouse, France.. pp. 252-259. https://doi.org/10.3115/1073012.1073046","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.130","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P01/P01-1034.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.676","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ltg.ed.ac.uk/papers/01grover_acl.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.591.1182","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.591.1182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/alex/papers/acl2001.grover.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.6242","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.6242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ltg.ed.ac.uk/papers/01grover_acl.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7807556e-1db9-486c-9bf6-ad570f039c20","is_oa":true,"landing_page_url":"http://www.aclweb.org/anthology/P01-1034","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/1073012.1073046","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073046","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2095955690.pdf","grobid_xml":"https://content.openalex.org/works/W2095955690.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W22625483","https://openalex.org/W1509114999","https://openalex.org/W1513693800","https://openalex.org/W1612238087","https://openalex.org/W1809415035","https://openalex.org/W1968953480","https://openalex.org/W1972573551","https://openalex.org/W2026779664","https://openalex.org/W2038248725","https://openalex.org/W2071664212","https://openalex.org/W2082818164","https://openalex.org/W2089436184","https://openalex.org/W2093647425","https://openalex.org/W2129608356","https://openalex.org/W2130747650","https://openalex.org/W2154104658","https://openalex.org/W2158495215","https://openalex.org/W2952115222","https://openalex.org/W2953046001","https://openalex.org/W3089214111","https://openalex.org/W4245322178","https://openalex.org/W6672991609"],"related_works":["https://openalex.org/W2024164996","https://openalex.org/W2347497444","https://openalex.org/W1972245780","https://openalex.org/W2112528798","https://openalex.org/W2047342127","https://openalex.org/W4251156254","https://openalex.org/W9409462","https://openalex.org/W2918781068","https://openalex.org/W2921934746","https://openalex.org/W56340752"],"abstract_inverted_index":{"We":[0,51,70],"describe":[1,52],"the":[2,31,67,85],"use":[3],"of":[4,48,55,59],"XML":[5,74],"tokenisation,":[6],"tagging":[7],"and":[8,91],"mark-up":[9],"tools":[10,75],"to":[11,46,80,83],"prepare":[12],"a":[13,53,57,77],"corpus":[14],"for":[15],"parsing.":[16],"Our":[17],"techniques":[18],"are":[19,44],"generally":[20],"applicable":[21],"but":[22,40],"here":[23],"we":[24],"focus":[25],"on":[26],"parsing":[27],"Medline":[28],"abstracts":[29],"with":[30,66],"ANLT":[32],"wide-coverage":[33],"grammar.":[34],"Hand-crafted":[35],"grammars":[36],"inevitably":[37],"lack":[38],"coverage":[39,42],"many":[41],"failures":[43],"due":[45],"inadequacies":[47],"their":[49],"lexicons.":[50],"method":[54],"gaining":[56],"degree":[58],"robustness":[60],"by":[61],"interfacing":[62],"POS":[63],"tag":[64],"information":[65],"existing":[68],"lexicon.":[69],"also":[71],"show":[72],"that":[73],"provide":[76],"sophisticated":[78],"approach":[79],"pre-processing,":[81],"helping":[82],"ameliorate":[84],"'messiness'":[86],"in":[87],"real":[88],"language":[89],"data":[90],"improve":[92],"parse":[93],"performance.":[94]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}