東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Multilingual Transfer Learning for C...

Winata, Genta Indra.

FindBook

Google Book

Amazon

博客來

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling./
作者:	Winata, Genta Indra.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	121 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
Contained By:	Dissertations Abstracts International83-01B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28697796
ISBN:	9798534657739

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling.
Winata, Genta Indra.

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 121 p.

Source: Dissertations Abstracts International, Volume: 83-01, Section: B.

Thesis (Ph.D.)--Hong Kong University of Science and Technology (Hong Kong), 2021.

This item must not be sold to any third party vendors.

Multilingualism is the ability of a speaker to communicate natively in more than one language. In multilingual communities, switching languages within a conversation, called code-switching, commonly occurs, and this creates a demand for multilingual dialogue and speech recognition systems to cater to this need. However, understanding code-switching utterances is a very challenging task for these systems because the model has to adapt to code-switching styles. Deep learning approaches have enabled natural language systems to achieve significant improvement towards human-level performance on languages with huge amounts of training data in recent years. However, they are unable to support numerous low-resource languages, mainly mixed languages. Also, code-switching, despite being a frequent phenomenon, is a characteristic only of spoken language and thus lacks transcriptions required for training deep learning models. On the other hand, conventional approaches to solving the low-resource issue in codeswitching are focused on applying linguistic theories to the statistical model. The constraints defined in these theories are useful. Still, they cannot be postulated as a universal rule for all code-switching scenarios, especially for languages that are syntactically divergent, such as English and Mandarin. In this thesis, we address the aforementioned issues by proposing language-agnostic multitask training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information is judiciously extracted from high-resource monolingual speech data to the code-switching domain. The meta-transfer learning quickly adapts the model to the codeswitching task from a number of monolingual tasks by learning to learn in a multi-task learning fashion. Second, we propose a novel multilingual meta-embeddings approach to effectively represent code-switching data by acquiring useful knowledge learned in other languages, learning the commonalities of closely related languages and leveraging lexical composition. The method is far more efficient compared to contextualized pre-trained multilingual models. Third, we introduce multi-task learning to integrate syntactic information as a transfer learning strategy to a language model and learn where to code-switch. To further alleviate the issue of data scarcity and limitations of linguistic theory, we propose a data augmentation method using Pointer-Gen, a neural network using a copy mechanism to teach the model the code-switch points from monolingual parallel sentences, and we use the augmented data for multilingual transfer learning. We disentangle the need for linguistic theory, and the model captures code-switching points by attending to input words and aligning the parallel words, without requiring any word alignments or constituency parsers. More importantly, the model can be effectively used for languages that are syntactically different, such as English and Mandarin, and it outperforms the linguistic theory-based models. In essence, we effectively tackle the data scarcity issue by introducing multilingual transfer learning methods to transfer knowledge from high-resource languages to the code-switching domain, and we compare their effectiveness with the conventional methods using linguistic theories.

ISBN: 9798534657739Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Code switching

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling.
LDR:04487nmm a2200349 4500 001 2282115
005 20210927083544.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798534657739
035 $a (MiAaPQ)AAI28697796
035 $a (MiAaPQ)HongKongSciTech_991012936363903412
035 $a AAI28697796
040 $a MiAaPQ $c MiAaPQ
100 1 $a Winata, Genta Indra. $3 3560870
245 1 0 $a Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 121 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
500 $a Advisor: Fung, Pascale.
502 $a Thesis (Ph.D.)--Hong Kong University of Science and Technology (Hong Kong), 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Multilingualism is the ability of a speaker to communicate natively in more than one language. In multilingual communities, switching languages within a conversation, called code-switching, commonly occurs, and this creates a demand for multilingual dialogue and speech recognition systems to cater to this need. However, understanding code-switching utterances is a very challenging task for these systems because the model has to adapt to code-switching styles. Deep learning approaches have enabled natural language systems to achieve significant improvement towards human-level performance on languages with huge amounts of training data in recent years. However, they are unable to support numerous low-resource languages, mainly mixed languages. Also, code-switching, despite being a frequent phenomenon, is a characteristic only of spoken language and thus lacks transcriptions required for training deep learning models. On the other hand, conventional approaches to solving the low-resource issue in codeswitching are focused on applying linguistic theories to the statistical model. The constraints defined in these theories are useful. Still, they cannot be postulated as a universal rule for all code-switching scenarios, especially for languages that are syntactically divergent, such as English and Mandarin. In this thesis, we address the aforementioned issues by proposing language-agnostic multitask training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information is judiciously extracted from high-resource monolingual speech data to the code-switching domain. The meta-transfer learning quickly adapts the model to the codeswitching task from a number of monolingual tasks by learning to learn in a multi-task learning fashion. Second, we propose a novel multilingual meta-embeddings approach to effectively represent code-switching data by acquiring useful knowledge learned in other languages, learning the commonalities of closely related languages and leveraging lexical composition. The method is far more efficient compared to contextualized pre-trained multilingual models. Third, we introduce multi-task learning to integrate syntactic information as a transfer learning strategy to a language model and learn where to code-switch. To further alleviate the issue of data scarcity and limitations of linguistic theory, we propose a data augmentation method using Pointer-Gen, a neural network using a copy mechanism to teach the model the code-switch points from monolingual parallel sentences, and we use the augmented data for multilingual transfer learning. We disentangle the need for linguistic theory, and the model captures code-switching points by attending to input words and aligning the parallel words, without requiring any word alignments or constituency parsers. More importantly, the model can be effectively used for languages that are syntactically different, such as English and Mandarin, and it outperforms the linguistic theory-based models. In essence, we effectively tackle the data scarcity issue by introducing multilingual transfer learning methods to transfer knowledge from high-resource languages to the code-switching domain, and we compare their effectiveness with the conventional methods using linguistic theories.
590 $a School code: 1223.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Linguistics. $3 524476
650 4 $a Datasets. $3 3541416
650 4 $a Teaching methods. $3 595505
650 4 $a Chinese languages. $3 3560871
653 $a Code switching
653 $a Multilingualism
690 $a 0984
690 $a 0800
690 $a 0290
710 2 $a Hong Kong University of Science and Technology (Hong Kong). $3 1022235
773 0 $t Dissertations Abstracts International $g 83-01B.
790 $a 1223
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28697796