{"id":{"repo_id":"aachen","oai_identifier":"oai:publications.rwth-aachen.de:58741"},"canonical_url":"https://search.dev.ndltd.org/etd/aachen/oai:publications.rwth-aachen.de:58741","repository":{"repo_id":"aachen","name":"RWTH Aachen University","base_url":"https://publications.rwth-aachen.de/oai2d"},"display":{"title":"Statistical machine translation : from single-word models to alignment templates","abstract":"In this work, new approaches for machine translation using statistical methods are described. In addition to the standard source-channel approach to statistical machine translation, a more general approach based on the maximum entropy principle is presented. Various methods for computing single-word alignments using statistical or heuristic models are described. Various smoothing techniques, methods to integrate a conventional dictionary and training methods are analyzed. A detailed evaluation of these models is performed by comparing the automatically produced word alignment with a manually produced reference alignment. Based on these fundamental single-word based alignment models, a new phrase-based translation model - the alignment template model - is suggested. For this model, a training and an efficient search algorithm is developed. For two specific applications (interactive translation and multi-source translation) specific search algorithms are developed. The suggested machine translation approach has been tested for the German-English Verbmobil task, the French-English Hansards task and for Chinese-English news text translation. Often, the obtained results have been significantly better than those obtained with alternative approaches to machine translation.","abstract_html":"In this work, new approaches for machine translation using statistical methods are described. In addition to the standard source-channel approach to statistical machine translation, a more general approach based on the maximum entropy principle is presented. Various methods for computing single-word alignments using statistical or heuristic models are described. Various smoothing techniques, methods to integrate a conventional dictionary and training methods are analyzed. A detailed evaluation of these models is performed by comparing the automatically produced word alignment with a manually produced reference alignment. Based on these fundamental single-word based alignment models, a new phrase-based translation model - the alignment template model - is suggested. For this model, a training and an efficient search algorithm is developed. For two specific applications (interactive translation and multi-source translation) specific search algorithms are developed. The suggested machine translation approach has been tested for the German-English Verbmobil task, the French-English Hansards task and for Chinese-English news text translation. Often, the obtained results have been significantly better than those obtained with alternative approaches to machine translation.","abstract_has_math":false,"creators":["Och, Franz Josef"],"institution":"Publikationsserver der RWTH Aachen University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Ney, Hermann"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2002,"date_issued":"2002","date_published":"2002","updated_at":"2026-07-30T19:42:31Z","subjects":["info:eu-repo/classification/ddc/004","Informatik","statistical machine translation","alignment models","maximum entropy"],"languages":["eng"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-120579%22"],"render_values":[{"text":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-120579%22","href":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-120579%22","code":true}]}]},"links":{"outbound_url":"https://publications.rwth-aachen.de/record/58741","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ney, Hermann"]},{"key":"dc:creator","label":"Author","values":["Och, Franz Josef"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:coverage","label":"Dc Coverage","values":["DE"]},{"key":"dc:date","label":"Dc Date","values":["2002"]},{"key":"dc:publisher","label":"Institution","values":["Publikationsserver der RWTH Aachen University"]},{"key":"dc:relation","label":"Dc Relation","values":["info:eu-repo/semantics/altIdentifier/doi/10.18154/RWTH-CONV-120579","info:eu-repo/semantics/altIdentifier/urn/urn:nbn:de:hbz:82-opus-5291"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/doctoralThesis","info:eu-repo/semantics/publishedVersion"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["info:eu-repo/classification/ddc/004","Informatik","statistical machine translation","alignment models","maximum entropy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://publications.rwth-aachen.de/record/58741","https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-120579%22"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this work, new approaches for machine translation using statistical methods are described. In addition to the standard source-channel approach to statistical machine translation, a more general approach based on the maximum entropy principle is presented. Various methods for computing single-word alignments using statistical or heuristic models are described. Various smoothing techniques, methods to integrate a conventional dictionary and training methods are analyzed. A detailed evaluation of these models is performed by comparing the automatically produced word alignment with a manually produced reference alignment. Based on these fundamental single-word based alignment models, a new phrase-based translation model - the alignment template model - is suggested. For this model, a training and an efficient search algorithm is developed. For two specific applications (interactive translation and multi-source translation) specific search algorithms are developed. The suggested machine translation approach has been tested for the German-English Verbmobil task, the French-English Hansards task and for Chinese-English news text translation. Often, the obtained results have been significantly better than those obtained with alternative approaches to machine translation."]},{"key":"dc:source","label":"Dc Source","values":["Aachen : Publikationsserver der RWTH Aachen University IX, 144 S. (2002). doi:10.18154/RWTH-CONV-120579 = Aachen, Techn. Hochsch., Diss., 2002"]},{"key":"dc:title","label":"Title","values":["Statistical machine translation : from single-word models to alignment templates"]}]}],"canonical_facts":{"dc:contributor":["Ney, Hermann"],"dc:coverage":["DE"],"dc:creator":["Och, Franz Josef"],"dc:date":["2002"],"dc:description":["In this work, new approaches for machine translation using statistical methods are described. In addition to the standard source-channel approach to statistical machine translation, a more general approach based on the maximum entropy principle is presented. Various methods for computing single-word alignments using statistical or heuristic models are described. Various smoothing techniques, methods to integrate a conventional dictionary and training methods are analyzed. A detailed evaluation of these models is performed by comparing the automatically produced word alignment with a manually produced reference alignment. Based on these fundamental single-word based alignment models, a new phrase-based translation model - the alignment template model - is suggested. For this model, a training and an efficient search algorithm is developed. For two specific applications (interactive translation and multi-source translation) specific search algorithms are developed. The suggested machine translation approach has been tested for the German-English Verbmobil task, the French-English Hansards task and for Chinese-English news text translation. Often, the obtained results have been significantly better than those obtained with alternative approaches to machine translation."],"dc:identifier":["https://publications.rwth-aachen.de/record/58741","https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-120579%22"],"dc:language":["eng"],"dc:publisher":["Publikationsserver der RWTH Aachen University"],"dc:relation":["info:eu-repo/semantics/altIdentifier/doi/10.18154/RWTH-CONV-120579","info:eu-repo/semantics/altIdentifier/urn/urn:nbn:de:hbz:82-opus-5291"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:source":["Aachen : Publikationsserver der RWTH Aachen University IX, 144 S. (2002). doi:10.18154/RWTH-CONV-120579 = Aachen, Techn. Hochsch., Diss., 2002"],"dc:subject":["info:eu-repo/classification/ddc/004","Informatik","statistical machine translation","alignment models","maximum entropy"],"dc:title":["Statistical machine translation : from single-word models to alignment templates"],"dc:type":["info:eu-repo/semantics/doctoralThesis","info:eu-repo/semantics/publishedVersion"]},"updated_at":"2026-07-30T19:42:31Z"}