{"id":"https://openalex.org/W2000748429","doi":"https://doi.org/10.3115/1609067.1609161","title":"Feature-based method for document alignment in comparable news corpora","display_name":"Feature-based method for document alignment in comparable news corpora","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2000748429","doi":"https://doi.org/10.3115/1609067.1609161","mag":"2000748429"},"language":"en","primary_location":{"id":"doi:10.3115/1609067.1609161","doi":"https://doi.org/10.3115/1609067.1609161","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1609067.1609161","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1609067.1609161","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.5555/1609067.1609161","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056497976","display_name":"Thuy Vu","orcid":"https://orcid.org/0000-0003-1056-6975","observed_orcids":["https://orcid.org/0000-0003-1056-6975"]},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thuy Vu","raw_affiliation_strings":["Institute for Infocomm Research, South Tower, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, South Tower, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":"https://orcid.org/0000-0002-2347-0879","observed_orcids":["https://orcid.org/0000-0002-2347-0879"]},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ai Ti Aw","raw_affiliation_strings":["Institute for Infocomm Research, South Tower, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, South Tower, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402925","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-6059-3798","observed_orcids":["https://orcid.org/0000-0002-6059-3798"]},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Institute for Infocomm Research, South Tower, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, South Tower, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":2.5808,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.90693241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0024999999441206455,"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":0.0003000000142492354,"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/comparable-corpora","display_name":"comparable corpora","score":0.9710000157356262},{"id":"https://openalex.org/keywords/news-articles","display_name":"news articles","score":0.7829999923706055},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"discrete Fourier transform","score":0.7910000085830688},{"id":"https://openalex.org/keywords/pearson-correlation","display_name":"Pearson correlation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"bilingual dictionary","score":0.8809999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079318404197693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7210909724235535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7028175592422485},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5598701238632202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5554848909378052},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5059346556663513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.463808536529541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39028269052505493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13392633199691772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08006599545478821},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1609067.1609161","doi":"https://doi.org/10.3115/1609067.1609161","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1609067.1609161","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1609067.1609161","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.1164","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.1164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/E/E09/E09-1096.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1609067.1609161","doi":"https://doi.org/10.3115/1609067.1609161","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1609067.1609161","pdf_url":"https://dl.acm.org/doi/pdf/10.5555/1609067.1609161","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on - EACL '09","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2000748429.pdf","grobid_xml":"https://content.openalex.org/works/W2000748429.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W30647502","https://openalex.org/W111745025","https://openalex.org/W1482214997","https://openalex.org/W1494864219","https://openalex.org/W1499049447","https://openalex.org/W1937758960","https://openalex.org/W2063646365","https://openalex.org/W2092094655","https://openalex.org/W2119013622","https://openalex.org/W2135399361","https://openalex.org/W2136542423","https://openalex.org/W2137757165","https://openalex.org/W2151521349","https://openalex.org/W2152397572","https://openalex.org/W2166606631","https://openalex.org/W2233998645","https://openalex.org/W2400876794","https://openalex.org/W4240913316","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W341091098","https://openalex.org/W1848122268","https://openalex.org/W2518598732","https://openalex.org/W7047315992","https://openalex.org/W147399331","https://openalex.org/W2967526790","https://openalex.org/W2514208185","https://openalex.org/W2511852057","https://openalex.org/W1997742772","https://openalex.org/W2120623612"],"abstract_inverted_index":{"In":[0,92],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,103,129],"feature-based":[6],"method":[7,86,109],"to":[8,80],"align":[9],"documents":[10],"with":[11,128],"similar":[12],"content":[13],"across":[14],"two":[15,89,121],"sets":[16,122],"of":[17,29,37,47,115,123],"bilingual":[18,48,104,124],"comparable":[19,58,90],"corpora":[20,60,125],"from":[21],"daily":[22],"news":[23,59],"texts.":[24],"We":[25],"evaluate":[26],"the":[27,35,45,54,88,120],"contribution":[28],"each":[30],"individual":[31],"feature":[32,71],"and":[33,41,56,78,97,117],"investigate":[34],"incorporation":[36],"these":[38],"diverse":[39],"statistical":[40,98],"heuristic":[42,96],"features":[43,99],"for":[44],"task":[46],"document":[49],"alignment.":[50],"Experimental":[51],"results":[52],"on":[53,87,119],"English-Chinese":[55],"English-Malay":[57],"show":[61],"that":[62],"our":[63,108],"proposed":[64],"Discrete":[65],"Fourier":[66],"Transform-based":[67],"term":[68],"frequency":[69],"distribution":[70],"is":[72],"very":[73],"effective.":[74],"It":[75],"contributes":[76],"4.1%":[77],"8%":[79],"performance":[81,113],"improvement":[82,114],"over":[83],"Pearson's":[84],"correlation":[85],"corpora.":[91],"addition,":[93],"when":[94,126],"more":[95],"as":[100,102],"well":[101],"dictionary":[105],"are":[106],"utilized,":[107],"shows":[110],"an":[111],"absolute":[112],"23.2%":[116],"15.3%":[118],"comparing":[127],"prior":[130],"information":[131],"retrieval-based":[132],"method.":[133]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}
