東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Generalizing Low-Resource Morphology...

Wiemerslage, Adam J.,

Linked to FindBook

Google Book

Amazon

博客來

Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection // Adam J Wiemerslage.
Author:	Wiemerslage, Adam J.,
Description:	1 electronic resource (214 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
Contained By:	Dissertations Abstracts International86-11B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31940506
ISBN:	9798315702948

Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection /
Wiemerslage, Adam J.,

Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection /Adam J Wiemerslage. - 1 electronic resource (214 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: B.

State of the art NLP methods to leverage enormous amounts of digital text are transforming the experience of working with computers and accessing the internet for many people. However, for most of the world's languages, there is insufficient digital data to make recently popular technology like large language models (LLMs) possible. New technology like LLMs are typically not well-suited for underrepresented languages-often referred to as low-resource languages in NLP-without sufficient digital data. In this case, simpler language technologies like dictionaries, morphological analyzers, and text normalizers are useful. This is especially apparent for language documentary life-cycles, building educational tools, and the development of language typology databases. With this in mind, we propose techniques for automatically expanding coverage of morphological databases and develop methods for building morphological tools for the large set of languages with few available resources. We then study the generation capabilities of neural network models that learn from these resources. Finally we propose methods for training neural networks when only small amounts of data are available, taking inspiration from the recent successes of self-supervised pretraining in high-resource NLP.

English

ISBN: 9798315702948Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Natural language processing

Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection /
LDR:02785nmm a22004213i 4500 001 2433294
005 20250825104043.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315702948
035 $a (MiAaPQD)AAI31940506
035 $a AAI31940506
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Wiemerslage, Adam J., $e author. $3 3822845
245 1 0 $a Generalizing Low-Resource Morphology: Cognitive and Neural Perspectives on Inflection / $c Adam J Wiemerslage.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (214 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: 86-11, Section: B.
500 $a Advisors: von der Wense, Katharina Committee members: Palmer, Alexis; Palmer, Martha; Pacheco, Maria; Gorman, Kyle.
502 $b Ph.D. $c University of Colorado at Boulder $d 2025.
520 $a State of the art NLP methods to leverage enormous amounts of digital text are transforming the experience of working with computers and accessing the internet for many people. However, for most of the world's languages, there is insufficient digital data to make recently popular technology like large language models (LLMs) possible. New technology like LLMs are typically not well-suited for underrepresented languages-often referred to as low-resource languages in NLP-without sufficient digital data. In this case, simpler language technologies like dictionaries, morphological analyzers, and text normalizers are useful. This is especially apparent for language documentary life-cycles, building educational tools, and the development of language typology databases. With this in mind, we propose techniques for automatically expanding coverage of morphological databases and develop methods for building morphological tools for the large set of languages with few available resources. We then study the generation capabilities of neural network models that learn from these resources. Finally we propose methods for training neural networks when only small amounts of data are available, taking inspiration from the recent successes of self-supervised pretraining in high-resource NLP.
546 $a English
590 $a School code: 0051
650 4 $a Computer science. $3 523869
650 4 $a Linguistics. $3 524476
650 4 $a Morphology. $3 591167
653 $a Natural language processing
653 $a Large language models
653 $a Neural network models
653 $a Morphological databases
690 $a 0984
690 $a 0290
690 $a 0287
710 2 $a University of Colorado at Boulder. $b Computer Science. $e degree granting institution. $3 3818604
720 1 $a von der Wense, Katharina $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11B.
790 $a 0051
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31940506