{"id":"https://openalex.org/W2145251161","doi":"https://doi.org/10.3115/1220175.1220237","title":"A DOM tree alignment model for mining parallel data from the web","display_name":"A DOM tree alignment model for mining parallel data from the web","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2145251161","doi":"https://doi.org/10.3115/1220175.1220237","mag":"2145251161"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220237","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1220237&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100666184","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-5215-025X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Lei Shi","raw_affiliation_strings":["Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111632482","display_name":"Cheng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Cheng Niu","raw_affiliation_strings":["Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701575","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0003-0696-767X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, 5F Sigma Center, 49 Zhichun Road, Beijing 10080, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA","Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100666184"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":6.5129,"has_fulltext":true,"cited_by_count":85,"citation_normalized_percentile":{"value":0.96465831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.8439635634422302},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.7780234217643738},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.6272896528244019},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6264216899871826},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.6016634702682495},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.5331883430480957},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4795410633087158},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4599546194076538},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3954535722732544},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36297228932380676},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2559746503829956},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07194894552230835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439635634422302},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.7780234217643738},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.6272896528244019},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6264216899871826},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.6016634702682495},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.5331883430480957},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4795410633087158},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4599546194076538},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3954535722732544},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36297228932380676},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2559746503829956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07194894552230835},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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:10.3115/1220175.1220237","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.8895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.8895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P06/P06-1062.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220237","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2145251161.pdf","grobid_xml":"https://content.openalex.org/works/W2145251161.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W8895266","https://openalex.org/W157432847","https://openalex.org/W1490123432","https://openalex.org/W1788726640","https://openalex.org/W1819903106","https://openalex.org/W1978470410","https://openalex.org/W2006969979","https://openalex.org/W2024181699","https://openalex.org/W2047295649","https://openalex.org/W2096894677","https://openalex.org/W2104103102","https://openalex.org/W2115755647","https://openalex.org/W2116316001","https://openalex.org/W2116713744","https://openalex.org/W2117652747","https://openalex.org/W2124262992","https://openalex.org/W2138553032","https://openalex.org/W2138584836","https://openalex.org/W2143927888","https://openalex.org/W2145262681","https://openalex.org/W2158388102","https://openalex.org/W2160842254","https://openalex.org/W2165691108","https://openalex.org/W2166098990","https://openalex.org/W2168929382","https://openalex.org/W2911427979","https://openalex.org/W2963761463","https://openalex.org/W4245826738","https://openalex.org/W7036656038"],"related_works":["https://openalex.org/W2245616560","https://openalex.org/W2351804282","https://openalex.org/W2048998278","https://openalex.org/W1556894713","https://openalex.org/W158130761","https://openalex.org/W1490416172","https://openalex.org/W2588706232","https://openalex.org/W2031790754","https://openalex.org/W2096877906","https://openalex.org/W2379693035"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,25,29],"new":[4,71],"web":[5,20,56],"mining":[6,64,72,76,79],"scheme":[7,73],"for":[8],"parallel":[9,46,53,55,87],"data":[10],"acquisition.":[11],"Based":[12],"on":[13],"the":[14,38,51,66,75,83],"Document":[15],"Object":[16],"Model":[17],"(DOM),":[18],"page":[21],"is":[22,34],"represented":[23],"as":[24],"DOM":[26,30,47],"tree.":[27],"Then":[28],"tree":[31],"alignment":[32],"model":[33],"proposed":[35],"to":[36],"identify":[37],"translationally":[39],"equivalent":[40],"texts":[41],"and":[42,81],"hyperlinks":[43],"between":[44],"two":[45],"trees.":[48],"By":[49],"tracing":[50],"identified":[52],"hyperlinks,":[54],"documents":[57],"are":[58],"recursively":[59],"mined.":[60],"Compared":[61],"with":[62],"previous":[63],"schemes,":[65],"benchmarks":[67],"show":[68],"that":[69],"this":[70],"improves":[74],"coverage,":[77],"reduces":[78],"bandwidth,":[80],"enhances":[82],"quality":[84],"of":[85],"mined":[86],"sentences.":[88]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}