{"id":"https://openalex.org/W97242617","doi":"https://doi.org/10.63317/3b5c7yah6g4r","title":"Mining the Web for Discourse Markers","display_name":"Mining the Web for Discourse Markers","publication_year":2004,"publication_date":"2004-05-01","ids":{"openalex":"https://openalex.org/W97242617","doi":"https://doi.org/10.63317/3b5c7yah6g4r","mag":"97242617"},"language":"en","primary_location":{"id":"doi:10.63317/3b5c7yah6g4r","doi":"https://doi.org/10.63317/3b5c7yah6g4r","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3b5c7yah6g4r","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ben Hutchinson","orcid":null,"observed_orcids":[]},"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":true,"raw_author_name":"Ben Hutchinson","raw_affiliation_strings":["School of Informatics University of Edinburgh 2 Buccleuch Place , Edinburgh EH8 9LW , Scotland , UK","University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh 2 Buccleuch Place , Edinburgh EH8 9LW , Scotland , UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh","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":1.2957,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78441084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9911999702453613,"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":0.9911999702453613,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.002199999988079071,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0008999999845400453,"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/discourse-markers","display_name":"discourse markers","score":1.0},{"id":"https://openalex.org/keywords/web-mining","display_name":"web mining","score":0.7310000061988831},{"id":"https://openalex.org/keywords/automatic-identification","display_name":"automatic identification","score":0.5709999799728394},{"id":"https://openalex.org/keywords/corpus-collection","display_name":"corpus collection","score":0.4959999918937683},{"id":"https://openalex.org/keywords/balanced-corpus","display_name":"balanced corpus","score":0.5789999961853027},{"id":"https://openalex.org/keywords/human-performance-comparison","display_name":"human performance comparison","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481472492218018},{"id":"https://openalex.org/C90464235","wikidata":"https://www.wikidata.org/wiki/Q1051521","display_name":"Discourse marker","level":2,"score":0.7086156010627747},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6472606062889099},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5047918558120728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4229356646537781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3142268657684326},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08773055672645569},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.63317/3b5c7yah6g4r","doi":"https://doi.org/10.63317/3b5c7yah6g4r","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3b5c7yah6g4r","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.8530","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.8530","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/s0130702/papers/LREC04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.7182","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.7182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","raw_type":"text"},{"id":"mag:97242617","doi":null,"is_oa":false,"landing_page_url":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/3b5c7yah6g4r","doi":"https://doi.org/10.63317/3b5c7yah6g4r","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3b5c7yah6g4r","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2004/pdf/333.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W97242617.pdf","grobid_xml":"https://content.openalex.org/works/W97242617.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W262828805","https://openalex.org/W1483817654","https://openalex.org/W1814652019","https://openalex.org/W1938088002","https://openalex.org/W2014516359","https://openalex.org/W2097491141","https://openalex.org/W2106108275","https://openalex.org/W2109783296","https://openalex.org/W2124416056","https://openalex.org/W2135441635","https://openalex.org/W2152197045","https://openalex.org/W2153804780","https://openalex.org/W2598654328"],"related_works":["https://openalex.org/W7096320617","https://openalex.org/W3086423516","https://openalex.org/W2804289704","https://openalex.org/W7084148332","https://openalex.org/W7095426728","https://openalex.org/W2971285462","https://openalex.org/W7098677142","https://openalex.org/W2965863117","https://openalex.org/W3028600070","https://openalex.org/W2774438446"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,71],"methodology":[4,17],"for":[5,21],"obtaining":[6],"sentences":[7],"containing":[8],"discourse":[9,26,35,61],"markers":[10,62],"from":[11],"the":[12,31,58,64],"World":[13],"Wide":[14],"Web.The":[15],"proposed":[16],"is":[18],"particularly":[19],"suitable":[20],"collecting":[22],"large":[23],"numbers":[24],"of":[25,34,50,52,60],"marker":[27],"tokens.It":[28],"relies":[29],"on":[30,63],"automatic":[32],"identification":[33],"markers,":[36],"and":[37],"we":[38],"show":[39,56],"that":[40,51,57],"this":[41],"can":[42],"be":[43],"done":[44],"with":[45,68],"an":[46],"accuracy":[47],"within":[48],"9%":[49],"human":[53],"performance.We":[54],"also":[55],"distribution":[59],"web":[65],"correlates":[66],"highly":[67],"those":[69],"in":[70],"conventional":[72],"balanced":[73],"corpus.":[74]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
