{"id":"https://openalex.org/W4416034732","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.680","title":"Text Anomaly Detection with Simplified Isolation Kernel","display_name":"Text Anomaly Detection with Simplified Isolation Kernel","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034732","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.680"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.680","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.680","pdf_url":"https://aclanthology.org/2025.findings-emnlp.680.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.680.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052456633","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0003-2184-4491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083492296","display_name":"Sikun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sikun Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020953714","display_name":"Yujiu Yang","orcid":"https://orcid.org/0000-0002-6427-1024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujiu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006514077","display_name":"Lianyong Qi","orcid":"https://orcid.org/0000-0001-9875-9856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianyong Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343852","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0001-6239-1180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29967194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12702","last_page":"12713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.3176000118255615,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.3176000118255615,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.07320000231266022,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.07209999859333038,"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/anomaly-detection","display_name":"Anomaly detection","score":0.5604000091552734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.516700029373169},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.32089999318122864},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.3001999855041504},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.27900001406669617}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5665000081062317},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2892000079154968},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.680","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.680","pdf_url":"https://aclanthology.org/2025.findings-emnlp.680.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.680","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.680","pdf_url":"https://aclanthology.org/2025.findings-emnlp.680.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034732.pdf","grobid_xml":"https://content.openalex.org/works/W4416034732.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Two-step":[0],"approaches":[1],"combining":[2],"pre-trained":[3],"large":[4,28],"language":[5,29],"model":[6],"embeddings":[7,25,56],"and":[8,38,70,102,107],"anomaly":[9,16,64,95],"detectors":[10],"demonstrate":[11,84],"strong":[12],"performance":[13,90],"in":[14],"text":[15],"detection":[17,89,96],"by":[18,27],"leveraging":[19],"rich":[20],"semantic":[21],"representations.However,":[22],"highdimensional":[23],"dense":[24,55],"extracted":[26],"models":[30],"pose":[31],"challenges":[32],"due":[33],"to":[34,57],"substantial":[35],"memory":[36,104],"requirements":[37],"high":[39],"computation":[40],"time.To":[41],"address":[42],"this":[43],"challenge,":[44],"we":[45],"introduce":[46],"the":[47],"Simplified":[48],"Isolation":[49],"Kernel":[50],"(SIK),":[51],"which":[52],"maps":[53],"high-dimensional":[54],"lower-dimensional":[58],"sparse":[59],"representations":[60],"while":[61,98],"preserving":[62],"crucial":[63],"characteristics.SIK":[65],"has":[66],"linear":[67],"time":[68],"complexity":[69,74],"significantly":[71],"reduces":[72],"space":[73],"through":[75],"its":[76],"innovative":[77],"boundary-focused":[78],"feature":[79],"mapping.Experiments":[80],"across":[81],"7":[82],"datasets":[83],"that":[85],"SIK":[86],"achieves":[87],"better":[88],"than":[91],"11":[92],"state-of-the-art":[93],"(SOTA)":[94],"algorithms":[97],"maintaining":[99],"computational":[100],"efficiency":[101],"low":[103],"cost.All":[105],"code":[106],"demonstrations":[108],"are":[109],"available":[110],"at":[111],"https://github.com/charles-cao/SIK.":[112]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}