{"id":"https://openalex.org/W2055209900","doi":"https://doi.org/10.1109/fskd.2013.6816269","title":"Measuring domain similarity for statistical machine translation","display_name":"Measuring domain similarity for statistical machine translation","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2055209900","doi":"https://doi.org/10.1109/fskd.2013.6816269","mag":"2055209900"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2013.6816269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2013.6816269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 10th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","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/A5021179252","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0001-9335-1368"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040038124","display_name":"Hailong Cao","orcid":"https://orcid.org/0000-0002-6842-8674"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Cao","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021179252"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08955669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2001","issue":null,"first_page":"611","last_page":"615"},"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":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9688000082969666,"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":0.7560338973999023},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7501409649848938},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7236828207969666},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6897086501121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6400043964385986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5181021094322205},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.5153273940086365},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4937172830104828},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.47459882497787476},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46719762682914734},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44136518239974976},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4233565330505371},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4225376844406128},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41233348846435547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3719356060028076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33431094884872437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17734676599502563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560338973999023},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7501409649848938},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7236828207969666},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6897086501121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6400043964385986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5181021094322205},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.5153273940086365},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4937172830104828},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.47459882497787476},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46719762682914734},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44136518239974976},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4233565330505371},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4225376844406128},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41233348846435547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3719356060028076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33431094884872437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17734676599502563},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2013.6816269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2013.6816269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 10th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)","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":22,"referenced_works":["https://openalex.org/W21337280","https://openalex.org/W106601280","https://openalex.org/W1534872089","https://openalex.org/W1574901103","https://openalex.org/W1880262756","https://openalex.org/W1982662198","https://openalex.org/W1989658336","https://openalex.org/W2124807415","https://openalex.org/W2136477195","https://openalex.org/W2137387514","https://openalex.org/W2142746600","https://openalex.org/W2146950091","https://openalex.org/W2171119909","https://openalex.org/W2334889010","https://openalex.org/W2394860946","https://openalex.org/W4237791300","https://openalex.org/W6600894851","https://openalex.org/W6631944917","https://openalex.org/W6645800779","https://openalex.org/W6680917135","https://openalex.org/W6712079609","https://openalex.org/W7056650509"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W97789383","https://openalex.org/W4289406402","https://openalex.org/W2727156679","https://openalex.org/W3087516072","https://openalex.org/W2067997904","https://openalex.org/W2364071303","https://openalex.org/W3145048402","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"It":[0,20],"is":[1,15,21,52],"well":[2],"known":[3,23],"that":[4,24,114],"the":[5,25,28,32,36,39,48,67,116,121,126,130,134,137],"statistical":[6],"machine":[7],"translation":[8],"(SMT)":[9],"performance":[10],"suffers":[11],"when":[12],"a":[13,101],"model":[14],"applied":[16],"to":[17,56,82],"out-of-domain":[18],"data.":[19,60],"also":[22],"more":[26,37],"similar":[27],"test":[29],"domain":[30,34],"and":[31,71,84,107,124,140],"training":[33,40,59],"are,":[35],"efficient":[38],"data":[41,143],"are":[42,100],"for":[43,90],"SMT":[44,92],"performance.":[45],"Hence,":[46],"measuring":[47],"similarity":[49,69,87,97,109,131],"of":[50,76,103],"domains":[51],"an":[53],"important":[54],"task":[55],"select":[57],"appropriate":[58],"The":[61,74,111],"most":[62],"widely":[63],"used":[64],"method":[65],"uses":[66],"cosine":[68],"function":[70,132],"word":[72,118],"frequency.":[73],"lack":[75],"exploring":[77],"other":[78],"approaches":[79],"motivates":[80],"us":[81],"propose":[83],"compare":[85],"several":[86],"measures.":[88],"Aiming":[89],"better":[91],"performance,":[93],"we":[94],"compared":[95],"10":[96,138],"measures,":[98],"which":[99],"combination":[102],"2":[104],"feature":[105,122],"representations":[106],"5":[108],"functions.":[110],"results":[112],"show":[113],"using":[115,125],"relative":[117],"frequency":[119],"as":[120,129],"representation":[123],"skew":[127],"divergence":[128],"performs":[133],"best":[135],"amongst":[136],"measures":[139],"outperforms":[141],"random":[142],"selection.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}