{"id":"https://openalex.org/W2054789535","doi":"https://doi.org/10.1145/1871437.1871651","title":"Alignment of short length parallel corpora with an application to web search","display_name":"Alignment of short length parallel corpora with an application to web search","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2054789535","doi":"https://doi.org/10.1145/1871437.1871651","mag":"2054789535"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Jitendra Ajmera","raw_affiliation_strings":["IBM India Research Lab, New Delhi, India","IBM, India Research Lab., New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM, India Research Lab., New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064400393","display_name":"Hema Swetha Koppula","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hema Swetha Koppula","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069768149","display_name":"Krishna P. Leela","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishna P. Leela","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011855684","display_name":"Shibnath Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shibnath Mukherjee","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081863472","display_name":"Mehul Parsana","orcid":"https://orcid.org/0009-0008-6857-0858"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mehul Parsana","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063781689"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1106196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1477","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9983000159263611,"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":0.8581900596618652},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.643880307674408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914822220802307},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5652977824211121},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5105322599411011},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48759642243385315},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4699651896953583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4528809189796448},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4213620722293854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3642175495624542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8581900596618652},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.643880307674408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914822220802307},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5652977824211121},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5105322599411011},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48759642243385315},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4699651896953583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4528809189796448},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4213620722293854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3642175495624542},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W200075660","https://openalex.org/W2001306626","https://openalex.org/W2069870183","https://openalex.org/W2139273454","https://openalex.org/W2146446188","https://openalex.org/W2147880316","https://openalex.org/W2170741935","https://openalex.org/W6608156005"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2111726165","https://openalex.org/W2347460059","https://openalex.org/W1984858032","https://openalex.org/W2616891703","https://openalex.org/W4301042974"],"abstract_inverted_index":{"With":[0],"evolving":[1],"Web,":[2],"short":[3,26],"length":[4,27],"parallel":[5,28,46],"corpora":[6,29,47],"is":[7,41,55,63,80,97,148],"becoming":[8],"very":[9],"common":[10],"and":[11,104,129,151,163,175],"some":[12],"of":[13,53,89,101,115,133,194],"these":[14],"include":[15],"user":[16],"queries,":[17],"web":[18],"snippets":[19],"etc.":[20],"This":[21,40],"paper":[22],"concerns":[23],"situations":[24],"where":[25,48],"has":[30],"to":[31,36,43,64,82,112,159,171],"be":[32,65],"analyzed":[33],"in":[34,59,125,140,191],"order":[35],"find":[37],"meaningful":[38,192],"unit-alignment.":[39],"similar":[42,93],"dealing":[44],"with":[45],"a":[49],"sentence":[50],"level":[51],"alignment":[52,62,106],"translations":[54],"required,":[56],"but":[57],"differs":[58],"that":[60,100,185],"the":[61,95,113,117,126,155,186,195],"inferred":[66],"at":[67],"unit":[68,85,142],"(word":[69],"or":[70,91],"phrase)":[71],"level.":[72],"A":[73],"Conditional":[74],"Random":[75],"Field":[76],"(CRF)":[77],"based":[78,120],"approach":[79,188],"proposed":[81,187],"discover":[83],"this":[84,135,169],"alignment.":[86,143],"Given":[87],"pairs":[88],"semantically":[90],"syntactically":[92],"entities,":[94],"problem":[96],"formulated":[98],"as":[99],"mutual":[102,109,136],"segmentation":[103,110,137],"sequence":[105],"problem.":[107],"The":[108,131],"refers":[111],"process":[114,132],"segmenting":[116],"first":[118],"entity":[119,128],"on":[121],"units":[122],"(or":[123],"labels)":[124],"second":[127],"vice-versa.":[130],"optimizing":[134],"also":[138],"results":[139,190],"optimal":[141],"Since":[144],"our":[145,182],"training":[146],"data":[147,162],"not":[149],"segmented":[150],"unit-aligned,":[152],"we":[153],"modify":[154],"CRF":[156],"objective":[157],"function":[158],"accommodate":[160],"unsupervised":[161],"iterative":[164],"learning.":[165],"We":[166],"have":[167],"applied":[168],"framework":[170],"Web":[172],"Search":[173],"domain":[174],"specifically":[176],"for":[177],"query":[178],"reformulation":[179],"task.":[180],"Finally,":[181],"experiments":[183],"suggest":[184],"indeed":[189],"alternatives":[193],"original":[196],"query.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}