{"id":"https://openalex.org/W2250940209","doi":"https://doi.org/10.3115/v1/e14-1004","title":"Maximizing Component Quality in Bilingual Word-Aligned Segmentations","display_name":"Maximizing Component Quality in Bilingual Word-Aligned Segmentations","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250940209","doi":"https://doi.org/10.3115/v1/e14-1004","mag":"2250940209"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-1004","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1004","pdf_url":"https://aclanthology.org/E14-1004.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-1004.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090482209","display_name":"Spyros Martzoukos","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Spyros Martzoukos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109059955","display_name":"Christof Monz","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christof Monz","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067287968","display_name":"Christophe Costa Flor\u00eancio","orcid":"https://orcid.org/0000-0001-8138-6643"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christophe Costa Florencio","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090482209"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4228,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76896253,"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":"30","last_page":"38"},"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":0.9995999932289124,"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":0.9922000169754028,"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/phrase","display_name":"Phrase","score":0.8499401807785034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596136331558228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7132391333580017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6782112121582031},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.640765368938446},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5581371784210205},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45887792110443115},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43460094928741455},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.43342190980911255},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4234287142753601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34982162714004517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16434335708618164}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8499401807785034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596136331558228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7132391333580017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782112121582031},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.640765368938446},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5581371784210205},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45887792110443115},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43460094928741455},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.43342190980911255},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4234287142753601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34982162714004517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16434335708618164},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/e14-1004","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1004","pdf_url":"https://aclanthology.org/E14-1004.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/a111ee96-656e-4fb8-ae1c-fec62667a203","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/maximizing-component-quality-in-bilingual-wordaligned-segmentations(a111ee96-656e-4fb8-ae1c-fec62667a203).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Martzoukos, S, Costa Flor\u00eancio, C & Monz, C 2014, Maximizing Component Quality in Bilingual Word-Aligned Segmentations. in S Wintner, S Goldwater & S Riezler (eds), EACL 2014: 14th Conference of the European Chapter of the Association for Computational Linguistics : proceedings of the conference: April 26-30, 2014, Gothenburg, Sweden. Stroudsburg, PA, pp. 30-38, European Chapter of the Association for Computational Linguistics (EACL) 2014, 26/04/14. < http://www.aclweb.org/anthology/E/E14/E14-1004.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/a111ee96-656e-4fb8-ae1c-fec62667a203","is_oa":true,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/maximizing-component-quality-in-bilingual-wordaligned-segmentations(a111ee96-656e-4fb8-ae1c-fec62667a203).html","pdf_url":"http://www.aclweb.org/anthology/E/E14/E14-1004.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Martzoukos, S, Costa Flor\u00eancio, C & Monz, C 2014, Maximizing Component Quality in Bilingual Word-Aligned Segmentations. in S Wintner, S Goldwater & S Riezler (eds), EACL 2014: 14th Conference of the European Chapter of the Association for Computational Linguistics : proceedings of the conference: April 26-30, 2014, Gothenburg, Sweden. Stroudsburg, PA, pp. 30-38, European Chapter of the Association for Computational Linguistics (EACL) 2014, 26/04/14. < http://www.aclweb.org/anthology/E/E14/E14-1004.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.685.4640","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.4640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilps.science.uva.nl/sites/ilps.science.uva.nl/files/E14-1004.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-1004","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-1004","pdf_url":"https://aclanthology.org/E14-1004.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 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5483342299","display_name":null,"funder_award_id":"FP7-ICT","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G8231709080","display_name":"Multi-Lingual Content Synchronization for Wikis","funder_award_id":"248531","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250940209.pdf","grobid_xml":"https://content.openalex.org/works/W2250940209.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W132913264","https://openalex.org/W259977959","https://openalex.org/W1502364872","https://openalex.org/W1517947178","https://openalex.org/W1579213680","https://openalex.org/W1591201057","https://openalex.org/W1631260214","https://openalex.org/W1661630950","https://openalex.org/W1736600331","https://openalex.org/W1847536016","https://openalex.org/W1985658808","https://openalex.org/W2013950795","https://openalex.org/W2041167939","https://openalex.org/W2101105183","https://openalex.org/W2115826669","https://openalex.org/W2117889403","https://openalex.org/W2124528696","https://openalex.org/W2124807415","https://openalex.org/W2129083353","https://openalex.org/W2132083787","https://openalex.org/W2143269898","https://openalex.org/W2146574666","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2250325467","https://openalex.org/W2270190199"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W3011059803","https://openalex.org/W2384400852","https://openalex.org/W2963259630","https://openalex.org/W2765271678","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2728761353","https://openalex.org/W2883671469"],"abstract_inverted_index":{"Given":[0],"a":[1,28,96,127],"pair":[2,130],"of":[3,12,26,42,68,80,99,106,111,118],"source":[4],"and":[5,54,71,87],"target":[6],"language":[7,52],"sentences":[8],"which":[9],"are":[10,93],"translations":[11],"each":[13],"other":[14],"with":[15,140],"known":[16],"word":[17,88],"alignments":[18],"between":[19],"them,":[20],"we":[21],"extract":[22],"bilingual":[23,58,73,112],"phrase-level":[24,113],"segmenta-tions":[25],"such":[27,119],"pair.":[29],"This":[30],"is":[31,63,75],"done":[32],"by":[33,137],"identi-fying":[34],"two":[35,91],"appropriate":[36],"measures":[37,92],"that":[38,83,133],"assess":[39],"the":[40,47,57,66,72,81,100,104],"quality":[41],"phrase":[43,85,129],"segments,":[44],"one":[45,55],"on":[46,56,65,77],"mono-lingual":[48],"level":[49],"for":[50,103],"both":[51],"sides,":[53],"level.":[59],"The":[60],"monolingual":[61],"mea-sure":[62],"based":[64,76],"notion":[67],"partition":[69],"refine-ments":[70],"measure":[74],"structural":[78],"properties":[79],"graph":[82],"repre-sents":[84],"segments":[86],"alignments.":[89],"These":[90],"incorporated":[94],"in":[95,121,143],"ba-sic":[97],"adaptation":[98],"Cross-Entropy":[101],"method":[102,132],"purpose":[105],"extracting":[107],"an":[108],"N-best":[109],"list":[110],"segmentations.":[114],"A":[115],"straight-forward":[116],"application":[117],"lists":[120],"Statistical":[122],"Machine":[123],"Translation":[124],"(SMT)":[125],"yields":[126],"conservative":[128],"extraction":[131],"reduces":[134],"phrase-table":[135],"sizes":[136],"90":[138],"%":[139],"insignificant":[141],"loss":[142],"translation":[144],"quality.":[145],"1":[146]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}