Methods, Evalutations and Resources for Multilingual Transfer Learning
Research output: Book/Report › Ph.D. thesis › Research
Standard
Methods, Evalutations and Resources for Multilingual Transfer Learning. / Kementchedjhieva, Yova Radoslavova.
Department of Computer Science, Faculty of Science, University of Copenhagen, 2021. 145 p.Research output: Book/Report › Ph.D. thesis › Research
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - BOOK
T1 - Methods, Evalutations and Resources for Multilingual Transfer Learning
AU - Kementchedjhieva, Yova Radoslavova
PY - 2021
Y1 - 2021
N2 - Language technology has transformed the way we write, the way we interact with our devices, and the way we share and consume information. This was made possible by advancements in the field of Natural Language Processing (NLP), a largely data-driven subfield of machine learning. Since data are limited for many of the tasks, domains and languages studied in NLP, transfer learning has gainedgreat prominence in the field as a way to alleviate data scarcity. This thesis presents work on methods, evaluations and resources for multilingual transfer learning. Our research shows how to improve and correctly evaluate cross-lingual embeddings obtained through alignment. It sheds light on the source of performance in cross-lingual transfer learning for dependency parsing. And it introduces two new resources for language generation tasks, one best viewed as a test bed for cross-domain transfer methods and the other, as a test bed for meta-learning techniques. This thesis contributes to efforts in NLP towards optimal transfer of knowledge across languages and highlights some remaining limitations.
AB - Language technology has transformed the way we write, the way we interact with our devices, and the way we share and consume information. This was made possible by advancements in the field of Natural Language Processing (NLP), a largely data-driven subfield of machine learning. Since data are limited for many of the tasks, domains and languages studied in NLP, transfer learning has gainedgreat prominence in the field as a way to alleviate data scarcity. This thesis presents work on methods, evaluations and resources for multilingual transfer learning. Our research shows how to improve and correctly evaluate cross-lingual embeddings obtained through alignment. It sheds light on the source of performance in cross-lingual transfer learning for dependency parsing. And it introduces two new resources for language generation tasks, one best viewed as a test bed for cross-domain transfer methods and the other, as a test bed for meta-learning techniques. This thesis contributes to efforts in NLP towards optimal transfer of knowledge across languages and highlights some remaining limitations.
M3 - Ph.D. thesis
BT - Methods, Evalutations and Resources for Multilingual Transfer Learning
PB - Department of Computer Science, Faculty of Science, University of Copenhagen
ER -
ID: 280552300