{"id":"https://openalex.org/W1999302842","doi":"https://doi.org/10.1145/2009916.2010103","title":"An investigation of decompounding for cross-language patent search","display_name":"An investigation of decompounding for cross-language patent search","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W1999302842","doi":"https://doi.org/10.1145/2009916.2010103","mag":"1999302842"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2010103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doras.dcu.ie/16447/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063045515","display_name":"Johannes Leveling","orcid":"https://orcid.org/0000-0003-0603-4191"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Johannes Leveling","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070783596","display_name":"Walid Magdy","orcid":"https://orcid.org/0000-0001-9676-1338"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Walid Magdy","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018481328","display_name":"Gareth J. F. Jones","orcid":"https://orcid.org/0000-0003-2923-8365"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Gareth J.F. Jones","raw_affiliation_strings":["Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063045515"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":2.6314,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90345565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1169","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8644151091575623},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.8621509075164795},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6850379705429077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6728823184967041},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6167830228805542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6114209294319153},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5833563208580017},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5269302129745483},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.468680202960968},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4307795763015747},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14912334084510803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644151091575623},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.8621509075164795},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6850379705429077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6728823184967041},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6167830228805542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114209294319153},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5833563208580017},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5269302129745483},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.468680202960968},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4307795763015747},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14912334084510803},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2009916.2010103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:doras.dcu.ie:16447","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401510","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:http://www.rian.ie/49401/","is_oa":true,"landing_page_url":"http://doras.dcu.ie/16447/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Leveling, Johannes ORCID: 0000-0003-0603-4191 &lt;https://orcid.org/0000-0003-0603-4191&gt;, Magdy, Walid and Jones, Gareth J.F. ORCID: 0000-0003-2923-8365 &lt;https://orcid.org/0000-0003-2923-8365&gt;  (2011) An investigation of decompounding for cross-language patent search.  In: The 34th Annual ACM SIGIR Conference, 24-28 Jul 2011, Beijing, China.","raw_type":"Other"}],"best_oa_location":{"id":"pmh:http://www.rian.ie/49401/","is_oa":true,"landing_page_url":"http://doras.dcu.ie/16447/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Leveling, Johannes ORCID: 0000-0003-0603-4191 &lt;https://orcid.org/0000-0003-0603-4191&gt;, Magdy, Walid and Jones, Gareth J.F. ORCID: 0000-0003-2923-8365 &lt;https://orcid.org/0000-0003-2923-8365&gt;  (2011) An investigation of decompounding for cross-language patent search.  In: The 34th Annual ACM SIGIR Conference, 24-28 Jul 2011, Beijing, China.","raw_type":"Other"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1576685422","https://openalex.org/W1594547331","https://openalex.org/W1988807567","https://openalex.org/W2000635479","https://openalex.org/W2011548984","https://openalex.org/W2016856586","https://openalex.org/W2091944322","https://openalex.org/W2916187765"],"related_works":["https://openalex.org/W1839123017","https://openalex.org/W4232115401","https://openalex.org/W1592594506","https://openalex.org/W2970828463","https://openalex.org/W3138512925","https://openalex.org/W117735687","https://openalex.org/W2917705549","https://openalex.org/W2915106852","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Decompounding":[0],"has":[1],"been":[2],"found":[3],"to":[4],"improve":[5],"information":[6],"retrieval":[7,25],"(IR)":[8],"effectiveness":[9],"in":[10],"general":[11],"domains":[12],"for":[13,45,51,87,101],"languages":[14],"such":[15,40],"as":[16,41],"German":[17],"or":[18],"Dutch.":[19],"We":[20],"investigate":[21],"if":[22],"cross-language":[23],"patent":[24],"can":[26,89],"profit":[27],"from":[28,78],"decompounding.":[29],"This":[30],"poses":[31],"two":[32],"challenges:":[33],"i)":[34],"There":[35],"may":[36,66],"be":[37],"few":[38],"resources":[39],"parallel":[42],"corpora":[43],"available":[44],"training":[46,103],"an":[47],"machine":[48],"translation":[49,73,88],"system":[50],"a":[52,58],"compounding":[53],"language.":[54],"ii)":[55],"Patents":[56],"have":[57],"specific":[59],"writing":[60],"style":[61],"and":[62,72,94],"vocabulary":[63],"(\"patentese\"),":[64],"which":[65],"affect":[67],"the":[68,79],"performance":[69,99],"of":[70],"decompounding":[71,85,96],"methods.":[74],"Experiments":[75],"on":[76],"data":[77],"CLEF-IP":[80],"2010":[81],"task":[82],"show":[83],"that":[84,95],"patents":[86],"overcome":[90],"out-of-vocabulary":[91],"problems":[92],"(OOV)":[93],"improves":[97],"IR":[98],"significantly":[100],"small":[102],"corpora.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
