{"id":"https://openalex.org/W2509928212","doi":"https://doi.org/10.18653/v1/w16-2375","title":"The ILSP/ARC submission to the WMT 2016 Bilingual Document Alignment Shared Task","display_name":"The ILSP/ARC submission to the WMT 2016 Bilingual Document Alignment Shared Task","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2509928212","doi":"https://doi.org/10.18653/v1/w16-2375","mag":"2509928212"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2375","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w16-2375","pdf_url":"https://doi.org/10.18653/v1/w16-2375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w16-2375","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035904366","display_name":"Vassilis Papavassiliou","orcid":"https://orcid.org/0009-0005-5256-6887"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vassilis Papavassiliou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048843230","display_name":"Prokopis Prokopidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prokopis Prokopidis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090401945","display_name":"Stelios Piperidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stelios Piperidis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035904366"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89024383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"739"},"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":0.9997000098228455,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8376538157463074},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7129613161087036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.630893886089325},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5940803289413452},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.5770105719566345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269140601158142},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.522754430770874},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5010387897491455},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.46661701798439026},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4306764602661133},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34749430418014526},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12250411510467529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376538157463074},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7129613161087036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.630893886089325},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5940803289413452},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.5770105719566345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269140601158142},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.522754430770874},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5010387897491455},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.46661701798439026},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4306764602661133},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34749430418014526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12250411510467529},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2375","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w16-2375","pdf_url":"https://doi.org/10.18653/v1/w16-2375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2375","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w16-2375","pdf_url":"https://doi.org/10.18653/v1/w16-2375","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104},{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2509928212.pdf","grobid_xml":"https://content.openalex.org/works/W2509928212.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1995127855","https://openalex.org/W2009847538","https://openalex.org/W2047295649","https://openalex.org/W2101336838","https://openalex.org/W2153488166","https://openalex.org/W2168873056","https://openalex.org/W2170716095","https://openalex.org/W2251069477","https://openalex.org/W2251114426","https://openalex.org/W2751318774"],"related_works":["https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2358294942","https://openalex.org/W2265955221","https://openalex.org/W4367460280","https://openalex.org/W97157637","https://openalex.org/W2574531235","https://openalex.org/W1501103110","https://openalex.org/W4386004667","https://openalex.org/W3013124564"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"ILSP-ARC-pv42,":[3],"the":[4,17,37,40,43,83,112],"Institute":[5],"for":[6,16],"Language":[7],"and":[8,12,29,90],"Speech":[9],"Processing/Athena":[10],"Research":[11],"Innovation":[13],"Center":[14],"submission":[15,47],"WMT":[18],"2016":[19],"Bilingual":[20],"Document":[21],"Alignment":[22],"shared":[23],"task.":[24,41],"We":[25,101],"describe":[26],"several":[27],"document":[28],"collection-aware":[30],"features":[31,77],"that":[32,93,107],"our":[33,46,71,118],"system":[34,72,119],"explored":[35],"in":[36,82,111],"context":[38],"of":[39,51,60,125],"On":[42],"test":[44,113],"dataset,":[45],"achieved":[48],"a":[49,121],"recall":[50,124],"84.93%,":[52],"even":[53],"though":[54],"it":[55],"does":[56],"not":[57],"make":[58],"use":[59],"any":[61],"language-specific":[62],"resources":[63],"like":[64],"bilingual":[65],"lexica":[66],"or":[67],"MT":[68],"output.":[69],"Instead,":[70],"is":[73],"based":[74],"on":[75],"shallow":[76],"(including":[78],"links":[79],"to":[80,105],"documents":[81],"same":[84],"webdomain,":[85],"URLs,":[86],"digits,":[87],"image":[88],"filenames":[89],"HTML":[91],"structure)":[92],"can":[94],"be":[95],"easily":[96],"extracted":[97],"from":[98],"web":[99],"documents.":[100],"also":[102],"present":[103],"examples":[104],"show":[106],"when":[108],"de-duplication":[109],"issues":[110],"dataset":[114],"are":[115],"properly":[116],"addressed,":[117],"reaches":[120],"significantly":[122],"higher":[123],"92.5%.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
