{"id":"https://openalex.org/W2161443453","doi":"https://doi.org/10.1145/1135777.1135834","title":"A web-based kernel function for measuring the similarity of short text snippets","display_name":"A web-based kernel function for measuring the similarity of short text snippets","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2161443453","doi":"https://doi.org/10.1145/1135777.1135834","mag":"2161443453"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","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/A5054695014","display_name":"Mehran Sahami","orcid":"https://orcid.org/0000-0001-9549-6974"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehran Sahami","raw_affiliation_strings":["Google Inc, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084633611","display_name":"Timothy D. Heilman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy D. Heilman","raw_affiliation_strings":["Google Inc, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":58.272,"has_fulltext":false,"cited_by_count":743,"citation_normalized_percentile":{"value":0.99933036,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996999979019165,"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":0.9939000010490417,"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":0.7429125308990479},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7009115815162659},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6398923397064209},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5336818099021912},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5031329989433289},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4003024101257324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.345915287733078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32899051904678345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11425977945327759},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07770511507987976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429125308990479},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7009115815162659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6398923397064209},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5336818099021912},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5031329989433289},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4003024101257324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.345915287733078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32899051904678345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11425977945327759},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07770511507987976},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W187060457","https://openalex.org/W1496147749","https://openalex.org/W1525341925","https://openalex.org/W1555156243","https://openalex.org/W1563088657","https://openalex.org/W1956559956","https://openalex.org/W1978394996","https://openalex.org/W1979459060","https://openalex.org/W1997841190","https://openalex.org/W1999817920","https://openalex.org/W2000145992","https://openalex.org/W2009202693","https://openalex.org/W2081748524","https://openalex.org/W2094028551","https://openalex.org/W2125972593","https://openalex.org/W2142845314","https://openalex.org/W2145001205","https://openalex.org/W2147152072","https://openalex.org/W2149684865","https://openalex.org/W2165612380","https://openalex.org/W2170654002","https://openalex.org/W2325227998","https://openalex.org/W2613433911","https://openalex.org/W4231856373","https://openalex.org/W6631459773","https://openalex.org/W6640862754","https://openalex.org/W6681124392"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2076713575","https://openalex.org/W2014996787"],"abstract_inverted_index":{"Determining":[0],"the":[1,46,68,96],"similarity":[2,16,47,78],"of":[3,84,90,98],"short":[4,32,49,69],"text":[5,33,50],"snippets,":[6],"such":[7,76],"as":[8],"search":[9,61,111],"queries,":[10],"works":[11],"poorly":[12],"with":[13],"traditional":[14],"document":[15],"measures":[17],"(e.g.,":[18],"cosine),":[19],"since":[20],"there":[21],"are":[22],"often":[23],"few,":[24],"if":[25],"any,":[26],"terms":[27],"in":[28,102],"common":[29],"between":[30,48],"two":[31],"snippets.":[34],"We":[35,93],"address":[36],"this":[37,72,99],"problem":[38],"by":[39,58],"introducing":[40],"a":[41,77,103],"novel":[42],"method":[43],"for":[44,67,106],"measuring":[45],"snippets":[51],"(even":[52],"those":[53],"without":[54],"any":[55],"overlapping":[56],"terms)":[57],"leveraging":[59],"web":[60],"results":[62],"to":[63,110],"provide":[64,88],"greater":[65],"context":[66],"texts.":[70],"In":[71],"paper,":[73],"we":[74],"define":[75],"kernel":[79,100],"function,":[80],"mathematically":[81],"analyze":[82],"some":[83],"its":[85,91],"properties,":[86],"and":[87],"examples":[89],"efficacy.":[92],"also":[94],"show":[95],"use":[97],"function":[101],"large-scale":[104],"system":[105],"suggesting":[107],"related":[108],"queries":[109],"engine":[112],"users.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":53},{"year":2015,"cited_by_count":59},{"year":2014,"cited_by_count":64},{"year":2013,"cited_by_count":84},{"year":2012,"cited_by_count":67}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}