Thesis (Selection of subject)Thesis (Selection of subject)(version: 384)
Thesis details
   Login via CAS
Neuronové modely pro vícejazyčnou inflexi
Thesis title in Czech: Neuronové modely pro vícejazyčnou inflexi
Thesis title in English: Neural Models for Multilingual Inflection
Academic year of topic announcement: 2023/2024
Thesis type: diploma thesis
Thesis language:
Department: Institute of Formal and Applied Linguistics (32-UFAL)
Supervisor: RNDr. Jana Straková, Ph.D.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 05.02.2024
Date of assignment: 05.02.2024
Confirmed by Study dept. on: 05.02.2024
Guidelines
Automatic inflection, a process of word formation in which a base word form (lemma) is modified to express grammatical categories, is a useful and researched task. The aim of this thesis is to research supervised deep learning models for automatic inflection in multiple languages. The focus of the experiments is multilinguality and potential future deployment in an open-source tool or webservice.
References
Goldman et al. (2023): SIGMORPHON–UniMorph 2023 Shared Task 0: Typologically Diverse Morphological Inflection

Kodner et al. (2022): SIGMORPHON–UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection

Tiago Pimentel et al. (2021): SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages

Nivre et al. (2020): Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection

Arya D. McCarthy (2020): UniMorph 3.0: Universal Morphology
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html