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

FindBook

Google Book

Amazon

博客來

Efficient Natural Language Processing With Limited Data and Resources.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Efficient Natural Language Processing With Limited Data and Resources./
作者:	Wang, Hong.
面頁冊數:	1 online resource (135 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30573717click for full text (PQDT)
ISBN:	9798380615990

Efficient Natural Language Processing With Limited Data and Resources.
Wang, Hong.

Efficient Natural Language Processing With Limited Data and Resources. - 1 online resource (135 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--University of California, Santa Barbara, 2023.

Includes bibliographical references

Natural language processing (NLP) has long been regarded as the pinnacle of artificial intelligence, aiming to achieve a comprehensive understanding of human languages. In recent years, the field has experienced significant advancements with the transition from rule-based approaches to deep learning methodologies. However, the standard approaches often rely on vast amounts of data for learning, highlighting the necessity for more data-efficient techniques. Additionally, effectively utilizing available resources while addressing the challenges of frequent model updates and safeguarding against malicious attacks that exploit limited resources presents another significant problem in NLP. This dissertation focuses on the development of efficient natural language processing (NLP) models under limited data and the effective utilization of available resources. In the first part, we address the challenge of learning models with limited data. For scenarios where only a few examples are available, we propose a meta-learning approach that leverages task-specific meta information to effectively learn new models. For cases with a moderate amount of data but still insufficient for more demanding tasks, we introduce self-supervised learning techniques to enhance performance by incorporating additional learning tasks from the available data. We also explore the limitations of even state-of-the-art language models, such as GPT-3, in handling out-of-distribution data shifts and propose a tutor-based learning approach that converts out-of-distribution problems into in-distribution ones through step-by-step demonstrations.In the second part, we shift our focus to optimizing resource utilization in NLP. Given the rapidly changing nature of the world, frequent updates of deployed models with new data are crucial. We present innovative approaches for effectively updating models in lifelong learning scenarios. As the adoption of large language models as backbone dialogue systems gains popularity, resource limitations become a significant concern. To counter malicious attacks, particularly Distributed Denial of Service (DDoS) attacks, we investigate the detection of bot imposters using a single question. By accurately distinguishing between human users and bots, our objective is to maximize resource allocation for real users and ensure uninterrupted service.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798380615990Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Natural language processingIndex Terms--Genre/Form:

542853
Electronic books.

Efficient Natural Language Processing With Limited Data and Resources.
LDR:03728nmm a2200373K 4500 001 2364612
005 20231130105852.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798380615990
035 $a (MiAaPQ)AAI30573717
035 $a AAI30573717
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Wang, Hong. $3 1086008
245 1 0 $a Efficient Natural Language Processing With Limited Data and Resources.
264 0 $c 2023
300 $a 1 online resource (135 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Yan, Xifeng.
502 $a Thesis (Ph.D.)--University of California, Santa Barbara, 2023.
504 $a Includes bibliographical references
520 $a Natural language processing (NLP) has long been regarded as the pinnacle of artificial intelligence, aiming to achieve a comprehensive understanding of human languages. In recent years, the field has experienced significant advancements with the transition from rule-based approaches to deep learning methodologies. However, the standard approaches often rely on vast amounts of data for learning, highlighting the necessity for more data-efficient techniques. Additionally, effectively utilizing available resources while addressing the challenges of frequent model updates and safeguarding against malicious attacks that exploit limited resources presents another significant problem in NLP. This dissertation focuses on the development of efficient natural language processing (NLP) models under limited data and the effective utilization of available resources. In the first part, we address the challenge of learning models with limited data. For scenarios where only a few examples are available, we propose a meta-learning approach that leverages task-specific meta information to effectively learn new models. For cases with a moderate amount of data but still insufficient for more demanding tasks, we introduce self-supervised learning techniques to enhance performance by incorporating additional learning tasks from the available data. We also explore the limitations of even state-of-the-art language models, such as GPT-3, in handling out-of-distribution data shifts and propose a tutor-based learning approach that converts out-of-distribution problems into in-distribution ones through step-by-step demonstrations.In the second part, we shift our focus to optimizing resource utilization in NLP. Given the rapidly changing nature of the world, frequent updates of deployed models with new data are crucial. We present innovative approaches for effectively updating models in lifelong learning scenarios. As the adoption of large language models as backbone dialogue systems gains popularity, resource limitations become a significant concern. To counter malicious attacks, particularly Distributed Denial of Service (DDoS) attacks, we investigate the detection of bot imposters using a single question. By accurately distinguishing between human users and bots, our objective is to maximize resource allocation for real users and ensure uninterrupted service.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
653 $a Natural language processing
653 $a Human languages
653 $a Data-efficient techniques
653 $a Meta-learning approach
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of California, Santa Barbara. $b Computer Science. $3 1018455
773 0 $t Dissertations Abstracts International $g 85-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30573717 $z click for full text (PQDT)