Similarity between Units of Natural Language The Transition from Coarse to Fine Estimation

2025-05-02 0 0 3.56MB 318 页 10玖币

侵权投诉

Similarity between Units of Natural Language:

The Transition from Coarse to Fine Estimation

Submitted by

MUWenchuan

Thesis Advisor

Dr. LIM Kwan Hui

arXiv:2210.14275v1 [cs.CL] 25 Oct 2022

A thesis submitted to the Singapore University of Technology and Design in fulﬁllment

of the requirement for the degree of Doctor of Philosophy

2022

PhD Thesis Examination Committee

TEC Chair: Prof. Yuen Chau

Main Advisor: Prof. Lim Kwan Hui

Internal TEC member 1: Prof. Mohan Rajesh Elara

Internal TEC member 2: Prof. Dorien Herremans

Abstract

Doctor of Philosophy

Similarity between Units of Natural Language: The Transition from Coarse to Fine

Estimation

by MUWenchuan

iii

Capturing the similarities between human language units is crucial for explaining how

humans associate different objects, and therefore its computation has received extensive attention,

research, and applications. With the ever-increasing amount of information around us, calculating

similarity becomes increasingly complex, especially in many cases, such as legal or medical

affairs, measuring similarity requires extra care and precision, as small acts within a language unit

can have signiﬁcant real-world effects. My research goal in this thesis is to develop regression

models that account for similarities between language units in a more reﬁned way.

Computation of similarity has come a long way, but approaches to debugging the measures

are often based on continually ﬁtting human judgment values. To this end, my goal is to develop

an algorithm that precisely catches loopholes in a similarity calculation. Furthermore, most

methods have vague deﬁnitions of the similarities they compute and are often difﬁcult to interpret.

The proposed framework addresses both shortcomings. Itconstantly improves the model through

catching different loopholes. In addition, every reﬁnement of the model provides a reasonable

explanation. The regression model introduced in this thesis is called progressively reﬁned

similarity computation, which combines attack testing with adversarial training. The similarity

regression model of this thesis achieves state-of-the-art performance in handling edge cases.

Chapter 2 is an introductory chapter on similarity computation in general. The main four chapters

of the thesis explore the applications of general similarities, how to capture their omissions, and

how to design a similarity model that can be reﬁned over time.

The ﬁrst practical work looks at applying similarity classify topics in online discussions on

social networking services such as Twitter. The popularity of these services, and the large number

of tweet, challenges the automatic topic detection models. To complicate matters, these topics

need to be identiﬁed in the absence of prior knowledge about their type and number, and expertise

is needed to tune numerous parameters. To address this challenge, I modiﬁed the cluster-based

topic modelling algorithm that is originally based on word networks and n-grams co-occurrence.

A more stable similarity scheme based on word embedding is used to construct networks, and the

reﬁned algorithm can better utilise community detection methods to determine topics.

Similarity so far takes a binary value, despite its regression value being calculated. Only a

medium level of precision is required to determine whether similar or not. However, regression

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

SimilaritybetweenUnitsofNaturalLanguage:TheTransitionfromCoarsetoFineEstimationSubmittedbyMUWenchuanThesisAdvisorDr.LIMKwanHuiiiAthesissubmittedtotheSingaporeUniversityofTechnologyandDesigninfulllmentoftherequirementforthedegreeofDoctorofPhilosophy2022iPhDThesisExaminationCommitteeTECChair:Prof.Yue...

展开>> 收起<<

Similarity between Units of Natural Language The Transition from Coarse to Fine Estimation.pdf

共318页,预览5页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

Similarity between Units of Natural Language The Transition from Coarse to Fine Estimation

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: