國立虎尾科技大學 |

Building Reliable and Robust Natural Language Processing Models : = Enhancing Understanding of Semantically Equivalent Texts.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Building Reliable and Robust Natural Language Processing Models :/
其他題名:	Enhancing Understanding of Semantically Equivalent Texts.
作者:	Huang, Kuan-Hao.
面頁冊數:	1 online resource (130 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
Contained By:	Dissertations Abstracts International84-12A.
標題:	Information science. -
電子資源:	click for full text (PQDT)
ISBN:	9798379615321

Building Reliable and Robust Natural Language Processing Models : = Enhancing Understanding of Semantically Equivalent Texts.
Huang, Kuan-Hao.

Building Reliable and Robust Natural Language Processing Models :Enhancing Understanding of Semantically Equivalent Texts. - 1 online resource (130 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: A.

Thesis (Ph.D.)--University of California, Los Angeles, 2023.

Includes bibliographical references

Recently, research in the natural language processing (NLP) domain has achieved remarkable advancements. Machines have become increasingly intelligent, achieving human performance in several NLP benchmarks. Despite its potential, recent studies demonstrate that NLP systems are not as reliable and robust as we expect and are sensitive to different levels of modifications to the input text, including word-level, syntax-level, and language-level. Those modifications do not alter the meaning of input text but would make NLP models behave very differently, which deviates from human expectations. This robustness issue results in challenges when applying NLP models to real-world applications and therefore becomes an important research question in recent years. In this thesis, we highlight the crucial role of understanding semantically equivalent texts in resolving the robustness issue of NLP models. We put emphasis on enhancing NLP models' comprehension of semantically equivalent texts while focusing specifically on improving the syntax-level robustness and language-level robustness of NLP models. The first part of this thesis focuses on enhancing syntax-level robustness by disentangling semantics and syntax when learning text representations. We propose three different ways to separate syntax from semantics: learning with paraphrase pairs, learning with unannotated texts, and learning with abstract meaning representations. By adopting these methods, NLP models become less sensitive to syntax and more robust to syntactic perturbations. In the second part of this thesis, we improve language-level robustness by considering the zero-shot cross-lingual setting. We propose two methods to enhance zero-shot cross-lingual transfer: robust training and the utilization of generation-based models. The proposed approaches in this dissertation effectively improve the reliability and robustness of NLP models.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379615321Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

MultilingualIndex Terms--Genre/Form:

554714
Electronic books.

Building Reliable and Robust Natural Language Processing Models : = Enhancing Understanding of Semantically Equivalent Texts.
LDR:03321ntm a22003857 4500 001 1146394
005 20240812064604.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379615321
035 $a (MiAaPQ)AAI30524986
035 $a AAI30524986
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Huang, Kuan-Hao. $3 1471778
245 1 0 $a Building Reliable and Robust Natural Language Processing Models : $b Enhancing Understanding of Semantically Equivalent Texts.
264 0 $c 2023
300 $a 1 online resource (130 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: 84-12, Section: A.
500 $a Advisor: Chang, Kai-Wei.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2023.
504 $a Includes bibliographical references
520 $a Recently, research in the natural language processing (NLP) domain has achieved remarkable advancements. Machines have become increasingly intelligent, achieving human performance in several NLP benchmarks. Despite its potential, recent studies demonstrate that NLP systems are not as reliable and robust as we expect and are sensitive to different levels of modifications to the input text, including word-level, syntax-level, and language-level. Those modifications do not alter the meaning of input text but would make NLP models behave very differently, which deviates from human expectations. This robustness issue results in challenges when applying NLP models to real-world applications and therefore becomes an important research question in recent years. In this thesis, we highlight the crucial role of understanding semantically equivalent texts in resolving the robustness issue of NLP models. We put emphasis on enhancing NLP models' comprehension of semantically equivalent texts while focusing specifically on improving the syntax-level robustness and language-level robustness of NLP models. The first part of this thesis focuses on enhancing syntax-level robustness by disentangling semantics and syntax when learning text representations. We propose three different ways to separate syntax from semantics: learning with paraphrase pairs, learning with unannotated texts, and learning with abstract meaning representations. By adopting these methods, NLP models become less sensitive to syntax and more robust to syntactic perturbations. In the second part of this thesis, we improve language-level robustness by considering the zero-shot cross-lingual setting. We propose two methods to enhance zero-shot cross-lingual transfer: robust training and the utilization of generation-based models. The proposed approaches in this dissertation effectively improve the reliability and robustness of NLP models.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Computer science. $3 573171
653 $a Multilingual
653 $a Natural language processing
653 $a Robustness
653 $a Semantics
653 $a Syntax
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0723
710 2 $a University of California, Los Angeles. $b Computer Science 0201. $3 1182286
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 84-12A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30524986 $z click for full text (PQDT)