{"id":"https://openalex.org/W4389519485","doi":"https://doi.org/10.18653/v1/2023.conll-1.32","title":"Alignment via Mutual Information","display_name":"Alignment via Mutual Information","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519485","doi":"https://doi.org/10.18653/v1/2023.conll-1.32"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.conll-1.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.conll-1.32","pdf_url":"https://aclanthology.org/2023.conll-1.32.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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.conll-1.32.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022352906","display_name":"S Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Shinjini Ghosh","raw_affiliation_strings":["MIT \u03b2 IBM"],"affiliations":[{"raw_affiliation_string":"MIT \u03b2 IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693798","display_name":"Yoon Kim","orcid":"https://orcid.org/0000-0002-4837-8411"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yoon Kim","raw_affiliation_strings":["MIT \u03b2 IBM"],"affiliations":[{"raw_affiliation_string":"MIT \u03b2 IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003156858","display_name":"Ram\u00f3n Fern\u00e1ndez Astudillo","orcid":"https://orcid.org/0000-0001-9443-2346"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ramon Fernandez Astudillo","raw_affiliation_strings":["MIT \u03b2 IBM"],"affiliations":[{"raw_affiliation_string":"MIT \u03b2 IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043295314","display_name":"Tahira Naseem","orcid":"https://orcid.org/0009-0009-0603-2760"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Tahira Naseem","raw_affiliation_strings":["MIT \u03b2 IBM"],"affiliations":[{"raw_affiliation_string":"MIT \u03b2 IBM","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070829652","display_name":"Jacob Andreas","orcid":"https://orcid.org/0000-0002-3141-5845"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Jacob Andreas","raw_affiliation_strings":["MIT \u03b2 IBM"],"affiliations":[{"raw_affiliation_string":"MIT \u03b2 IBM","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022352906"],"corresponding_institution_ids":["https://openalex.org/I4210109586"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5843148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"488","last_page":"497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9975000023841858,"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":0.7967506051063538},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.7541548013687134},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.7334908246994019},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6943439245223999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519802808761597},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6101638078689575},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5959045886993408},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.5927683711051941},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.5714025497436523},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4987967014312744},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.49495261907577515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20347478985786438},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.13653552532196045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967506051063538},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.7541548013687134},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.7334908246994019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6943439245223999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519802808761597},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6101638078689575},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5959045886993408},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.5927683711051941},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.5714025497436523},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4987967014312744},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.49495261907577515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20347478985786438},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.13653552532196045},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.conll-1.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.conll-1.32","pdf_url":"https://aclanthology.org/2023.conll-1.32.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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.conll-1.32","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.conll-1.32","pdf_url":"https://aclanthology.org/2023.conll-1.32.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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519485.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1979102019","https://openalex.org/W2013196554","https://openalex.org/W2097333193","https://openalex.org/W2116211107","https://openalex.org/W2140679639","https://openalex.org/W2158388102","https://openalex.org/W2250618788","https://openalex.org/W2251448685","https://openalex.org/W2401082558","https://openalex.org/W2437005631","https://openalex.org/W2604397416","https://openalex.org/W2605602459","https://openalex.org/W2739845275","https://openalex.org/W2890463005","https://openalex.org/W2896457183","https://openalex.org/W2952589943","https://openalex.org/W2962784628","https://openalex.org/W2964030814","https://openalex.org/W2964183327","https://openalex.org/W3034999214","https://openalex.org/W3035463087","https://openalex.org/W3122836184","https://openalex.org/W3175810841","https://openalex.org/W4238907713","https://openalex.org/W4287125387","https://openalex.org/W4288089799","https://openalex.org/W4289259401","https://openalex.org/W4298393544","https://openalex.org/W4307324487","https://openalex.org/W4385570199"],"related_works":["https://openalex.org/W2101924850","https://openalex.org/W2188315358","https://openalex.org/W4387724891","https://openalex.org/W2530029028","https://openalex.org/W4287238667","https://openalex.org/W3149287595","https://openalex.org/W2137853824","https://openalex.org/W2594350003","https://openalex.org/W2783047733","https://openalex.org/W3189092450"],"abstract_inverted_index":{"Many":[0],"language":[1],"learning":[2,29,116],"tasks":[3],"require":[4],"learners":[5],"to":[6,62,74,89,114,137],"infer":[7],"correspondences":[8],"between":[9,94],"data":[10],"in":[11,52,80,170],"two":[12,115],"modalities.":[13],"Often,":[14],"these":[15],"alignments":[16,122,136],"are":[17,55],"many-to-many":[18,64],"and":[19,40,96,127,130,141,154],"context-sensitive.":[20],"For":[21],"example,":[22],"translating":[23],"into":[24],"morphologically":[25],"rich":[26],"languages":[27],"requires":[28],"not":[30],"just":[31],"how":[32],"words,":[33],"but":[34],"morphemes,":[35],"should":[36],"be":[37],"translated;":[38],"words":[39],"morphemes":[41],"may":[42],"have":[43],"different":[44],"meanings":[45],"(or":[46],"groundings)":[47],"depending":[48],"on":[49,100],"the":[50],"context":[51],"which":[53],"they":[54],"used.":[56],"We":[57,110],"describe":[58],"an":[59,163],"information-theoretic":[60],"approach":[61,67,113,150],"context-sensitive,":[63],"alignment.":[65],"Our":[66],"first":[68],"trains":[69],"a":[70],"masked":[71],"sequence":[72],"model":[73,88],"place":[75],"distributions":[76],"over":[77],"missing":[78],"spans":[79,98,105],"(source,":[81],"target)":[82],"sequences.":[83],"Next,":[84],"it":[85,103],"uses":[86],"this":[87,112],"compute":[90],"pointwise":[91],"mutual":[92,108,160],"information":[93,161],"source":[95],"target":[97],"conditional":[99,159],"context.":[101],"Finally,":[102],"aligns":[104],"with":[106],"high":[107],"information.":[109],"apply":[111],"problems:":[117],"character-based":[118],"word":[119,143],"translation":[120],"(using":[121,135],"for":[123,166],"joint":[124],"morphological":[125],"segmentation":[126],"lexicon":[128],"learning)":[129],"visually":[131],"grounded":[132],"reference":[133],"resolution":[134],"jointly":[138],"localize":[139],"referents":[140],"learn":[142],"meanings).":[144],"In":[145],"both":[146,152],"cases,":[147],"our":[148],"proposed":[149],"outperforms":[151],"structured":[153],"neural":[155],"baselines,":[156],"showing":[157],"that":[158],"offers":[162],"effective":[164],"framework":[165],"formalizing":[167],"alignment":[168],"problems":[169],"general":[171],"domains.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-23T23:20:30.427331","created_date":"2025-10-10T00:00:00"}