{"id":"https://openalex.org/W4416251453","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228563","title":"A Low-Noise Web Content Extraction Framework for LLM Data Pipelines: Integrating XGBoost Classification and Reverse Coloring","display_name":"A Low-Noise Web Content Extraction Framework for LLM Data Pipelines: Integrating XGBoost Classification and Reverse Coloring","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251453","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228563"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100748071","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-3180-5971"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Peking University,Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School"],"affiliations":[{"raw_affiliation_string":"Peking University,Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658080","display_name":"Ziyan Zhang","orcid":"https://orcid.org/0000-0002-3748-1130"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lexi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lexi Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423805","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-5339-681X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Peking University,Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School"],"affiliations":[{"raw_affiliation_string":"Peking University,Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100748071"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46806936,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9259999990463257,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9259999990463257,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0215000007301569,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.008100000210106373,"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/pruning","display_name":"Pruning","score":0.569100022315979},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4650999903678894},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.43860000371932983},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3910999894142151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.382099986076355},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972999811172485},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3912000060081482},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":23,"referenced_works":["https://openalex.org/W1706374111","https://openalex.org/W1968937761","https://openalex.org/W1989338554","https://openalex.org/W1997197279","https://openalex.org/W2005646337","https://openalex.org/W2012575882","https://openalex.org/W2022045834","https://openalex.org/W2070493638","https://openalex.org/W2092442289","https://openalex.org/W2095968786","https://openalex.org/W2120101509","https://openalex.org/W2135479443","https://openalex.org/W2158051716","https://openalex.org/W2160189941","https://openalex.org/W2295598076","https://openalex.org/W2790149575","https://openalex.org/W3177057043","https://openalex.org/W4244895750","https://openalex.org/W4284691825","https://openalex.org/W4399647672","https://openalex.org/W4400762160","https://openalex.org/W4402671353","https://openalex.org/W4409657349"],"related_works":[],"abstract_inverted_index":{"Low-Information-density":[0],"webpages":[1],"present":[2],"significant":[3],"challenges":[4],"for":[5,25,138],"web":[6,134],"content":[7,38],"extraction,":[8],"often":[9],"yielding":[10],"fragmented":[11],"text":[12,110],"and":[13,71,89],"high":[14],"noise":[15],"levels\u2014issues":[16],"that":[17,41,80],"become":[18],"especially":[19],"critical":[20],"when":[21],"preparing":[22],"large-scale":[23,139],"corpora":[24],"training":[26,141],"Large":[27],"Language":[28],"Models":[29],"(LLMs).":[30],"In":[31],"this":[32,81],"paper,":[33],"we":[34],"introduce":[35],"a":[36,47,84],"low-noise":[37],"extraction":[39,91,131],"framework":[40],"integrates":[42],"node-level":[43],"XGBoost":[44],"classification":[45,120],"with":[46,122],"global":[48,123],"reverse":[49,98],"coloring":[50,99],"procedure.":[51],"Specifically,":[52],"our":[53],"method":[54],"first":[55],"classifies":[56],"noisy":[57],"nodes":[58],"by":[59],"learning":[60],"localized":[61],"DOM":[62,124],"features,":[63],"then":[64],"refines":[65],"these":[66],"predictions":[67],"via":[68],"subtree-level":[69],"merging":[70],"pruning":[72],"to":[73],"enforce":[74],"structural":[75],"consistency.":[76],"Experimental":[77],"results":[78],"show":[79],"approach":[82],"outperforms":[83],"variety":[85],"of":[86,117,132],"baseline":[87],"tools":[88],"LLM-driven":[90],"methods":[92],"across":[93],"multiple":[94],"metrics.":[95],"Notably,":[96],"the":[97,115],"step":[100],"substantially":[101],"mitigates":[102],"local":[103,119],"misclassifications":[104],"while":[105],"improving":[106],"coherence":[107],"in":[108],"extracted":[109],"blocks.":[111],"Our":[112],"findings":[113],"underscore":[114],"value":[116],"combining":[118],"signals":[121],"constraints,":[125],"thereby":[126],"enabling":[127],"more":[128],"robust,":[129],"efficient":[130],"high-quality":[133],"data\u2014an":[135],"essential":[136],"requirement":[137],"LLM":[140],"pipelines.":[142]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-14T00:00:00"}