{"id":"https://openalex.org/W2104438213","doi":"https://doi.org/10.1145/2350176.2350180","title":"Learning to extract chemical names based on random text generation and incomplete dictionary","display_name":"Learning to extract chemical names based on random text generation and incomplete dictionary","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2104438213","doi":"https://doi.org/10.1145/2350176.2350180","mag":"2104438213"},"language":"en","primary_location":{"id":"doi:10.1145/2350176.2350180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2350176.2350180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Data Mining in Bioinformatics","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/A5008360728","display_name":"Yan Su","orcid":"https://orcid.org/0000-0003-2262-0297"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Su Yan","raw_affiliation_strings":["IBM Almaden Research Lab, San Jose, CA","IBM Almaden Research Lab, San Jose, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089086163","display_name":"W. Scott Spangler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Scott Spangler","raw_affiliation_strings":["IBM Almaden Research Lab, San Jose, CA","IBM Almaden Research Lab, San Jose, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383140","display_name":"Ying Chen","orcid":"https://orcid.org/0009-0005-8351-6620"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["IBM Almaden Research Lab, San Jose, CA","IBM Almaden Research Lab, San Jose, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Lab, San Jose, CA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008360728"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":0.2627,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.57893499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.9972000122070312,"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":0.8064322471618652},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7236683368682861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6167392730712891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790078043937683},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5607880353927612},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5361637473106384},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5226835608482361},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.5107719898223877},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5069072842597961},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.43615198135375977},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3967438340187073},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06939965486526489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064322471618652},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7236683368682861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6167392730712891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790078043937683},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5607880353927612},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5361637473106384},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5226835608482361},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.5107719898223877},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5069072842597961},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.43615198135375977},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3967438340187073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06939965486526489},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2350176.2350180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2350176.2350180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th International Workshop on Data Mining in Bioinformatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W142136654","https://openalex.org/W1490056294","https://openalex.org/W1934019294","https://openalex.org/W1995875735","https://openalex.org/W2036671379","https://openalex.org/W2060603187","https://openalex.org/W2095596879","https://openalex.org/W2119821739","https://openalex.org/W2125838338","https://openalex.org/W2147880316","https://openalex.org/W2169986726","https://openalex.org/W2523973766","https://openalex.org/W2757163186","https://openalex.org/W4253573210","https://openalex.org/W6648982606"],"related_works":["https://openalex.org/W2916255597","https://openalex.org/W3006227201","https://openalex.org/W4289715253","https://openalex.org/W3091569222","https://openalex.org/W2075635421","https://openalex.org/W2999302224","https://openalex.org/W2384158492","https://openalex.org/W3106020419","https://openalex.org/W1495833002","https://openalex.org/W2118050188"],"abstract_inverted_index":{"Automatically":[0],"extracting":[1],"chemical":[2,63,75],"names":[3],"from":[4,94],"text":[5,43],"has":[6],"significant":[7],"value":[8],"to":[9,32,80,90],"biomedical":[10],"and":[11,98],"life":[12],"science":[13],"research.":[14],"A":[15],"major":[16],"barrier":[17],"in":[18],"this":[19],"task":[20,61],"is":[21],"the":[22,40,52,60,68],"difficulty":[23],"of":[24,54,62,70,74],"getting":[25],"a":[26,34],"sizable":[27],"good":[28],"quality":[29],"training":[30,57,87],"set":[31],"train":[33],"reliable":[35],"entity":[36,65],"extraction":[37],"model.":[38],"Leveraging":[39],"well-studied":[41],"random":[42],"generation":[44],"techniques":[45],"based":[46],"on":[47],"formal":[48],"grammars,":[49],"we":[50,77],"explore":[51],"idea":[53],"automatically":[55],"creating":[56],"sets":[58],"for":[59],"named":[64],"extraction.":[66],"Assuming":[67],"availability":[69],"an":[71],"incomplete":[72],"list":[73],"names,":[76],"are":[78],"able":[79],"generate":[81],"well-controlled,":[82],"random,":[83],"yet":[84],"realistic":[85],"chemical-like":[86],"documents.":[88],"Compared":[89],"state-of-the-art":[91],"models":[92],"learned":[93],"manually":[95],"labeled":[96],"data":[97],"rule-based":[99],"systems":[100],"using":[101],"real-world":[102],"data,":[103],"our":[104],"solutions":[105],"show":[106],"comparable":[107],"or":[108],"better":[109],"results,":[110],"with":[111],"least":[112],"human":[113],"effort.":[114]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}