{"id":"https://openalex.org/W1963537959","doi":"https://doi.org/10.1145/1816123.1816126","title":"Transferring structural markup across translations using multilingual alignment and projection","display_name":"Transferring structural markup across translations using multilingual alignment and projection","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W1963537959","doi":"https://doi.org/10.1145/1816123.1816126","mag":"1963537959"},"language":"en","primary_location":{"id":"doi:10.1145/1816123.1816126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","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/A5058212934","display_name":"David Bamman","orcid":"https://orcid.org/0009-0003-1171-9408"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Bamman","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066134932","display_name":"Alison Babeu","orcid":null},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alison Babeu","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112237032","display_name":"Gregory Crane","orcid":"https://orcid.org/0000-0001-6847-2811"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Crane","raw_affiliation_strings":["Tufts University, Medford, MA, USA","Tufts University, Medford, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, Medford, MA, USA#TAB#","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058212934"],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":2.3274,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89049377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"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":0.9991999864578247,"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":0.9969000220298767,"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/markup-language","display_name":"Markup language","score":0.8663598895072937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165267109870911},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7347670197486877},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5407003164291382},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5270881056785583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5167067050933838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40351200103759766},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25175243616104126}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8663598895072937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165267109870911},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7347670197486877},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5407003164291382},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5270881056785583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5167067050933838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40351200103759766},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25175243616104126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1816123.1816126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.179.3199","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.179.3199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.perseus.tufts.edu/publications/jcdl27-bamman.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.4285","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.4285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Edbamman/pubs/pdf/jcdl2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306100","display_name":"National Endowment for the Humanities","ror":"https://ror.org/02vdm1p28"},{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W45780694","https://openalex.org/W68697577","https://openalex.org/W86887328","https://openalex.org/W1524610104","https://openalex.org/W1533863963","https://openalex.org/W1548663377","https://openalex.org/W1603678606","https://openalex.org/W1605484680","https://openalex.org/W1625582487","https://openalex.org/W1625816508","https://openalex.org/W1810300402","https://openalex.org/W1819903106","https://openalex.org/W1906503946","https://openalex.org/W1973923101","https://openalex.org/W1973924286","https://openalex.org/W2006969979","https://openalex.org/W2067030316","https://openalex.org/W2079442239","https://openalex.org/W2080373976","https://openalex.org/W2111553511","https://openalex.org/W2111885854","https://openalex.org/W2115057736","https://openalex.org/W2125280523","https://openalex.org/W2127566020","https://openalex.org/W2134159029","https://openalex.org/W2141532438","https://openalex.org/W2143954309","https://openalex.org/W2147192413","https://openalex.org/W2149551320","https://openalex.org/W2156985047","https://openalex.org/W2162049050","https://openalex.org/W2165254367","https://openalex.org/W2169830728","https://openalex.org/W2394524245","https://openalex.org/W2398533612","https://openalex.org/W2607058949","https://openalex.org/W2618735189","https://openalex.org/W2802304870","https://openalex.org/W2998215494","https://openalex.org/W3029930867","https://openalex.org/W3169462865"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W4235354490","https://openalex.org/W2143258726","https://openalex.org/W2381082207","https://openalex.org/W2025266532","https://openalex.org/W2136793911","https://openalex.org/W1519732405","https://openalex.org/W1971521465","https://openalex.org/W2377737135","https://openalex.org/W2100702185"],"abstract_inverted_index":{"We":[0,48],"present":[1],"here":[2],"a":[3,102,117,123],"method":[4],"for":[5,25],"automatically":[6],"projecting":[7,72,89],"structural":[8],"information":[9],"across":[10],"translations,":[11,82],"including":[12],"canonical":[13],"citation":[14],"structure":[15],"(such":[16],"as":[17],"chapters":[18],"and":[19,27,29,60,65],"sections),":[20],"speaker":[21],"information,":[22],"quotations,":[23],"markup":[24],"people":[26],"places,":[28],"any":[30],"other":[31],"element":[32],"in":[33,45,116],"TEI-compliant":[34],"XML":[35,74],"that":[36,41],"delimits":[37],"spans":[38],"of":[39,70],"text":[40],"are":[42],"linguistically":[43],"symmetrical":[44],"two":[46,53],"languages.":[47],"evaluate":[49],"this":[50],"technique":[51],"on":[52],"datasets,":[54],"one":[55,61],"containing":[56,62,92],"perfectly":[57],"transcribed":[58,81],"texts":[59,91],"errorful":[63],"OCR,":[64],"achieve":[66],"an":[67,84],"accuracy":[68,86],"rate":[69,87],"88.2%":[71],"13,023":[73],"tags":[75],"from":[76],"source":[77],"documents":[78],"to":[79,90,100,108,122],"their":[80],"with":[83],"83.6%":[85],"when":[88],"uncorrected":[93],"OCR.":[94],"This":[95],"approach":[96],"has":[97],"the":[98,113],"potential":[99],"allow":[101],"highly":[103],"granular":[104],"multilingual":[105],"digital":[106],"library":[107],"be":[109],"bootstrapped":[110],"by":[111],"applying":[112],"knowledge":[114],"contained":[115],"small,":[118],"heavily":[119],"curated":[120],"collection":[121],"much":[124],"larger":[125],"but":[126],"unstructured":[127],"one.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}