{"id":"https://openalex.org/W2902931170","doi":"https://doi.org/10.1145/3281505.3281585","title":"Learning-based word segmentation for reliable text document retrieval and augmentation","display_name":"Learning-based word segmentation for reliable text document retrieval and augmentation","publication_year":2018,"publication_date":"2018-11-28","ids":{"openalex":"https://openalex.org/W2902931170","doi":"https://doi.org/10.1145/3281505.3281585","mag":"2902931170"},"language":"en","primary_location":{"id":"doi:10.1145/3281505.3281585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3281505.3281585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology","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/A5011963384","display_name":"Jean-Pierre Lomaliza","orcid":null},"institutions":[{"id":"https://openalex.org/I8991828","display_name":"Pukyong National University","ror":"https://ror.org/0433kqc49","country_code":"KR","type":"education","lineage":["https://openalex.org/I8991828"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jean-Pierre Lomaliza","raw_affiliation_strings":["Pukyong National University, Busan, South Korea"],"affiliations":[{"raw_affiliation_string":"Pukyong National University, Busan, South Korea","institution_ids":["https://openalex.org/I8991828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085724843","display_name":"Hanhoon Park","orcid":"https://orcid.org/0000-0002-6968-4565"},"institutions":[{"id":"https://openalex.org/I8991828","display_name":"Pukyong National University","ror":"https://ror.org/0433kqc49","country_code":"KR","type":"education","lineage":["https://openalex.org/I8991828"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanhoon Park","raw_affiliation_strings":["Pukyong National University, Busan, South Korea"],"affiliations":[{"raw_affiliation_string":"Pukyong National University, Busan, South Korea","institution_ids":["https://openalex.org/I8991828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011963384"],"corresponding_institution_ids":["https://openalex.org/I8991828"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14329547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8559550046920776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7659070491790771},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.6596428751945496},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.56137615442276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5379332900047302},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5136217474937439},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5063763856887817},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.49742868542671204},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4415622353553772},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4150477349758148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3896175026893616},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3071461021900177},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.17194154858589172},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.06459665298461914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559550046920776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7659070491790771},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.6596428751945496},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.56137615442276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5379332900047302},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5136217474937439},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5063763856887817},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.49742868542671204},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4415622353553772},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4150477349758148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896175026893616},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3071461021900177},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.17194154858589172},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.06459665298461914},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3281505.3281585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3281505.3281585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1534808658","https://openalex.org/W1987822854","https://openalex.org/W2152242636","https://openalex.org/W2162506249"],"related_works":["https://openalex.org/W2145036943","https://openalex.org/W2538371562","https://openalex.org/W3046994506","https://openalex.org/W2045631426","https://openalex.org/W2027019938","https://openalex.org/W2079058854","https://openalex.org/W1751894661","https://openalex.org/W2137763598","https://openalex.org/W4238415164","https://openalex.org/W2039135287"],"abstract_inverted_index":{"Imagine":[0],"that":[1,18],"one":[2],"may":[3],"have":[4],"access":[5],"to":[6,21,25,36],"a":[7,10,14,34,38,43],"part":[8],"of":[9],"text":[11],"document,":[12],"say":[13],"page,":[15],"and":[16],"from":[17],"would":[19],"want":[20],"identify":[22],"the":[23],"document":[24,40],"which":[26],"it":[27],"belongs.":[28],"In":[29],"such":[30],"cases,":[31],"there":[32],"is":[33],"need":[35],"perform":[37],"content-based":[39],"retrieval":[41],"in":[42],"large":[44],"database.":[45]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}