Show simple item record

Univerzální morfologická analýza s využitím reinforcement learning
dc.contributor.advisorZeman, Daniel
dc.creatorCardenas Acosta, Ronald Ahmed
dc.date.accessioned2020-02-25T10:55:10Z
dc.date.available2020-02-25T10:55:10Z
dc.date.issued2020
dc.identifier.urihttp://hdl.handle.net/20.500.11956/116656
dc.description.abstractThe persistent efforts to make valuable annotated corpora in more diverse, morphologically rich languages has driven research in NLP into considering more explicit techniques to incorporate morphological information into the pipeline. Recent efforts have proposed combined strategies to bring together the transducer paradigm and neural architectures, although ingesting one character at a time in a context-agnostic setup. In this thesis, we introduce a technique inspired by the byte pair encoding (BPE) compression algorithm in order to obtain transducing actions that resemble word formations more faithfully. Then, we propose a neural transducer architecture that operates over these transducing actions, ingesting one word token at a time and effectively incorporating sentential context by encoding per- token action representations in a hierarchical fashion. We investigate the benefit of this word formation representations for the tasks of lemmatization and context-aware morphological tagging for a typologically diverse set of languages, including a low- resourced native language from Peru, Shipibo-Konibo. For lemmatization, we use exploration-based optimization under a reinforcement learning framework, and find that our approach benefits greatly languages that use less commonly studied morphological processes...en_US
dc.languageEnglishcs_CZ
dc.language.isoen_US
dc.publisherUniverzita Karlova, Matematicko-fyzikální fakultacs_CZ
dc.subjectmorfologická analýzacs_CZ
dc.subjectreinforcement learningcs_CZ
dc.subjectmorphological analysisen_US
dc.subjectreinforcement learningen_US
dc.titleUniversal Morphological Analysis using ReinforcementLearningen_US
dc.typediplomová prácecs_CZ
dcterms.created2020
dcterms.dateAccepted2020-02-04
dc.description.departmentÚstav formální a aplikované lingvistikycs_CZ
dc.description.departmentInstitute of Formal and Applied Linguisticsen_US
dc.description.facultyFaculty of Mathematics and Physicsen_US
dc.description.facultyMatematicko-fyzikální fakultacs_CZ
dc.identifier.repId212057
dc.title.translatedUniverzální morfologická analýza s využitím reinforcement learningcs_CZ
dc.contributor.refereeMareček, David
thesis.degree.nameMgr.
thesis.degree.levelnavazující magisterskécs_CZ
thesis.degree.disciplineComputational Linguisticsen_US
thesis.degree.disciplineMatematická lingvistikacs_CZ
thesis.degree.programComputer Scienceen_US
thesis.degree.programInformatikacs_CZ
uk.thesis.typediplomová prácecs_CZ
uk.taxonomy.organization-csMatematicko-fyzikální fakulta::Ústav formální a aplikované lingvistikycs_CZ
uk.taxonomy.organization-enFaculty of Mathematics and Physics::Institute of Formal and Applied Linguisticsen_US
uk.faculty-name.csMatematicko-fyzikální fakultacs_CZ
uk.faculty-name.enFaculty of Mathematics and Physicsen_US
uk.faculty-abbr.csMFFcs_CZ
uk.degree-discipline.csMatematická lingvistikacs_CZ
uk.degree-discipline.enComputational Linguisticsen_US
uk.degree-program.csInformatikacs_CZ
uk.degree-program.enComputer Scienceen_US
thesis.grade.csVýborněcs_CZ
thesis.grade.enExcellenten_US
uk.abstract.enThe persistent efforts to make valuable annotated corpora in more diverse, morphologically rich languages has driven research in NLP into considering more explicit techniques to incorporate morphological information into the pipeline. Recent efforts have proposed combined strategies to bring together the transducer paradigm and neural architectures, although ingesting one character at a time in a context-agnostic setup. In this thesis, we introduce a technique inspired by the byte pair encoding (BPE) compression algorithm in order to obtain transducing actions that resemble word formations more faithfully. Then, we propose a neural transducer architecture that operates over these transducing actions, ingesting one word token at a time and effectively incorporating sentential context by encoding per- token action representations in a hierarchical fashion. We investigate the benefit of this word formation representations for the tasks of lemmatization and context-aware morphological tagging for a typologically diverse set of languages, including a low- resourced native language from Peru, Shipibo-Konibo. For lemmatization, we use exploration-based optimization under a reinforcement learning framework, and find that our approach benefits greatly languages that use less commonly studied morphological processes...en_US
uk.file-availabilityV
uk.grantorUniverzita Karlova, Matematicko-fyzikální fakulta, Ústav formální a aplikované lingvistikycs_CZ
thesis.grade.code1
uk.publication-placePrahacs_CZ


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record


© 2017 Univerzita Karlova, Ústřední knihovna, Ovocný trh 560/5, 116 36 Praha 1; email: admin-repozitar [at] cuni.cz

Za dodržení všech ustanovení autorského zákona jsou zodpovědné jednotlivé složky Univerzity Karlovy. / Each constituent part of Charles University is responsible for adherence to all provisions of the copyright law.

Upozornění / Notice: Získané informace nemohou být použity k výdělečným účelům nebo vydávány za studijní, vědeckou nebo jinou tvůrčí činnost jiné osoby než autora. / Any retrieved information shall not be used for any commercial purposes or claimed as results of studying, scientific or any other creative activities of any person other than the author.

DSpace software copyright © 2002-2015  DuraSpace
Theme by 
@mire NV