{"id":"https://openalex.org/W2252257187","doi":"https://doi.org/10.3115/v1/w14-5207","title":"Command-line utilities for managing and exploring annotated corpora","display_name":"Command-line utilities for managing and exploring annotated corpora","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252257187","doi":"https://doi.org/10.3115/v1/w14-5207","mag":"2252257187"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5207","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/w14-5207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT","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/A5079518059","display_name":"Joel Nothman","orcid":"https://orcid.org/0000-0003-1497-3842"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Joel Nothman","raw_affiliation_strings":["University of Sydney"],"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088679482","display_name":"Tim Dawborn","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tim Dawborn","raw_affiliation_strings":["University of Sydney"],"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024711700","display_name":"James Curran","orcid":"https://orcid.org/0000-0001-9637-0484"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"James R. Curran","raw_affiliation_strings":["University of Sydney"],"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079518059"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.422,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76977817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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":0.9955999851226807,"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/disk-formatting","display_name":"Disk formatting","score":0.8834978342056274},{"id":"https://openalex.org/keywords/unix","display_name":"Unix","score":0.8702001571655273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8676408529281616},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7936164140701294},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5248215794563293},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4279298782348633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3977227509021759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.294524222612381},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24627161026000977},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11904138326644897},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08213773369789124}],"concepts":[{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.8834978342056274},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.8702001571655273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676408529281616},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7936164140701294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5248215794563293},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4279298782348633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3977227509021759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.294524222612381},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24627161026000977},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11904138326644897},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08213773369789124},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-5207","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/w14-5207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.6686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.6686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-5207.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W1511055280","https://openalex.org/W2056569219","https://openalex.org/W2119885577","https://openalex.org/W2134585533","https://openalex.org/W2158077889","https://openalex.org/W2970030445"],"related_works":["https://openalex.org/W4244466418","https://openalex.org/W2104062382","https://openalex.org/W2162878363","https://openalex.org/W2389021890","https://openalex.org/W2479325685","https://openalex.org/W4245101192","https://openalex.org/W2048571117","https://openalex.org/W119810944","https://openalex.org/W4211001737","https://openalex.org/W4235593861"],"abstract_inverted_index":{"Users":[0],"of":[1,63],"annotated":[2,119],"corpora":[3],"frequently":[4],"perform":[5],"basic":[6,20],"operations":[7],"such":[8,98],"as":[9],"inspecting":[10],"the":[11,73],"available":[12],"annotations,":[13],"filtering":[14],"documents,":[15],"formatting":[16],"data,":[17],"and":[18,48,56,115],"aggregating":[19],"statistics":[21],"over":[22,31],"a":[23,53],"corpus.":[24],"While":[25],"these":[26],"may":[27],"be":[28],"easily":[29],"performed":[30],"flat":[32],"text":[33],"files":[34],"with":[35,89,105],"stream-processing":[36],"UNIX":[37,93],"tools,":[38],"similar":[39],"tools":[40,99],"for":[41,58,79,84,103,118],"structured":[42,59,106],"annotation":[43],"require":[44],"custom":[45],"design.":[46],"Dawborn":[47],"Curran":[49],"(2014)":[50],"have":[51,66],"developed":[52],"declarative":[54],"description":[55],"storage":[57,114],"annotation,":[60],"on":[61],"top":[62],"which":[64],"we":[65],"built":[67],"generic":[68],"command-line":[69],"utilities.":[70,94],"We":[71,95],"describe":[72],"most":[74],"useful":[75],"utilities":[76],"\u2013":[77,88],"some":[78],"quick":[80],"data":[81],"exploration,":[82],"others":[83],"high-level":[85],"corpus":[86],"management":[87],"reference":[90],"to":[91],"comparable":[92],"suggest":[96],"that":[97],"are":[100],"universally":[101],"valuable":[102],"working":[104],"corpora;":[107],"in":[108],"turn,":[109],"their":[110],"utility":[111],"promotes":[112],"common":[113],"distribution":[116],"formats":[117],"text.":[120],"1":[121]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
