{"id":"https://openalex.org/W7155514543","doi":"https://doi.org/10.1109/icsc67292.2026.00042","title":"Unsupervised Boilerplate Removal Using N-gram Sequence Analysis","display_name":"Unsupervised Boilerplate Removal Using N-gram Sequence Analysis","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7155514543","doi":"https://doi.org/10.1109/icsc67292.2026.00042"},"language":null,"primary_location":{"id":"doi:10.1109/icsc67292.2026.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","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/A5134549188","display_name":"Kishore Vanapalli","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kishore Vanapalli","raw_affiliation_strings":["Carleton University Ottawa,School of Information Technology,ON,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University Ottawa,School of Information Technology,ON,Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831674","display_name":"Shahzad Khan","orcid":"https://orcid.org/0000-0003-3217-9028"},"institutions":[{"id":"https://openalex.org/I4210089660","display_name":"Gnowit (Canada)","ror":"https://ror.org/008egk659","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210089660"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shahzad Khan","raw_affiliation_strings":["Gnowit Inc. Ottawa,ON,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gnowit Inc. Ottawa,ON,Canada","institution_ids":["https://openalex.org/I4210089660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087753797","display_name":"M. Omair Shafiq","orcid":"https://orcid.org/0000-0002-1859-8296"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"M. Omair Shafiq","raw_affiliation_strings":["Carleton University Ottawa,School of Information Technology,ON,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carleton University Ottawa,School of Information Technology,ON,Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62195352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.17980000376701355,"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":0.17980000376701355,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.11069999635219574,"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":0.04560000076889992,"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/sequence","display_name":"Sequence (biology)","score":0.43389999866485596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3260999917984009},{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.31290000677108765},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.28139999508857727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5062000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2502000033855438},{"id":"https://openalex.org/C2985264313","wikidata":"https://www.wikidata.org/wiki/Q378859","display_name":"Pattern analysis","level":2,"score":0.2484000027179718}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsc67292.2026.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc67292.2026.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Semantic Computing (ICSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-25T00:00:00"}
