{"id":"https://openalex.org/W2183189954","doi":null,"title":"Domain Adaptation in SMT of User-Generated Forum Content Guided by OOV Word Reduction: Normalization and/or Supplementary Data?","display_name":"Domain Adaptation in SMT of User-Generated Forum Content Guided by OOV Word Reduction: Normalization and/or Supplementary Data?","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2183189954","mag":"2183189954"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.3479","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.3479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.computing.dcu.ie/~away/PUBS/2012/40.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5107145381","display_name":"Pratyush Banerjee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Pratyush Banerjee","raw_affiliation_strings":["Dublin City University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070618344","display_name":"Sudip Kumar Naskar","orcid":"https://orcid.org/0000-0003-1588-4665","observed_orcids":["https://orcid.org/0000-0003-1588-4665"]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sudip Kumar Naskar","raw_affiliation_strings":["Dublin City University"],"raw_orcid":"https://orcid.org/0000-0003-1588-4665","affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070486143","display_name":"Johann Roturier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Johann Roturier","raw_affiliation_strings":["Dublin City University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055864641","display_name":"Andy Way","orcid":"https://orcid.org/0000-0001-5736-5930","observed_orcids":["https://orcid.org/0000-0001-5736-5930"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Way","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5736-5930","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944","observed_orcids":["https://orcid.org/0000-0003-1322-7944"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1322-7944","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2235,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9580336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0006000000284984708,"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/T10759","display_name":"Translation Studies and Practices","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.9549999833106995},{"id":"https://openalex.org/keywords/word-normalization","display_name":"word normalization","score":0.7300000190734863},{"id":"https://openalex.org/keywords/training-data-acquisition","display_name":"training data acquisition","score":0.5889999866485596},{"id":"https://openalex.org/keywords/noisy-data","display_name":"noisy data","score":0.4650000035762787},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8432992696762085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842632532119751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939998626708984},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5844094753265381},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5759702324867249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5661471486091614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3956104516983032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3930673897266388},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.3479","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.3479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.computing.dcu.ie/~away/PUBS/2012/40.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.3603","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.3603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nclt.dcu.ie/mt/papers/Banerjee_EAMT_2012.pdf","raw_type":"text"},{"id":"mag:2183189954","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/2012.eamt-1.41.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W22168010","https://openalex.org/W222053410","https://openalex.org/W635530177","https://openalex.org/W2101105183","https://openalex.org/W2117685088","https://openalex.org/W2124807415","https://openalex.org/W2146574666","https://openalex.org/W2149327368","https://openalex.org/W2153903004","https://openalex.org/W2156985047","https://openalex.org/W2172268343","https://openalex.org/W2356613612","https://openalex.org/W2394860946","https://openalex.org/W3202724003","https://openalex.org/W3202971710"],"related_works":["https://openalex.org/W152062518","https://openalex.org/W3171488001","https://openalex.org/W7095829359","https://openalex.org/W2963361183","https://openalex.org/W7099333382","https://openalex.org/W7056650509","https://openalex.org/W2401886177","https://openalex.org/W2182115895","https://openalex.org/W2137698233","https://openalex.org/W2250314498"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"a":[3,57,87],"set":[4,58],"of":[5,35,39,59,77,129],"domain":[6],"adaptation":[7],"techniques":[8,100],"for":[9,15,105,133],"improving":[10],"Statistical":[11],"Machine":[12],"Translation":[13],"(SMT)":[14],"usergenerated":[16],"web":[17],"forum":[18,107],"content.":[19],"We":[20,53,73],"investigate":[21,74],"both":[22,80],"normalization":[23,66,95,124,137],"and":[24,61,96,131],"supplementary":[25,68,97,111],"training":[26,51,69,98,112],"data":[27,113],"acquisition":[28,114],"techniques,":[29],"all":[30],"guided":[31],"by":[32],"the":[33,37,44,50,75],"aim":[34],"reducing":[36],"number":[38],"Out-Of-Vocabulary":[40],"(OOV)":[41],"items":[42],"in":[43,81],"target":[45],"language":[46],"with":[47],"respect":[48],"to":[49],"data.":[52],"classify":[54],"OOVs":[55],"into":[56],"types,":[60],"address":[62],"each":[63],"through":[64],"dedicated":[65],"and/or":[67],"material":[70,99],"selection-based":[71],"approaches.":[72],"effect":[76],"these":[78],"methods":[79],"an":[82],"additive":[83],"as":[84,86,117],"well":[85,118],"contrastive":[88],"scenario.":[89],"Our":[90],"findings":[91],"show":[92],"that":[93],"(i)":[94],"can":[101,115],"be":[102],"complementary,":[103],"(ii)":[104],"general":[106],"data,":[108,136],"fully":[109],"automatic":[110],"perform":[116],"or":[119],"sometimes":[120],"better":[121],"than":[122],"semi-automatic":[123],"(although":[125],"tackling":[126],"different":[127],"types":[128],"OOVs)":[130],"(iii)":[132],"very":[134],"noisy":[135],"really":[138],"pays":[139],"off.":[140],"1":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}