2026-09-19T13:48:12Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1538822024-03-22T03:10:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Williams, Sarah Nguyen, Thanh P. Q. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2024-03-21T19:13:20Z 2024-03-21T19:13:20Z 2024-02 2024-03-04T16:38:14.121Z https://hdl.handle.net/1721.1/153882 The rapid advancements in Artificial Intelligence (AI) have led to the development of complex and powerful models, resulting in opaque “black boxes” that hinder human understanding of their decision-making processes. This is especially true in the field of Natural Language Processing as large language models have become widely used and popularized in the form of chatbots and AI assistants. While there have been many attempts at explaining these models and concepts, most of them are directed at an audience already familiar with machine learning concepts. In this paper, I propose an approach to understanding existing concepts and models in NLP by simplifying them into intuitive narratives of towns and cities. By leveraging this more familiar context, the hope is to provide more engagement and information retention to non-technical audience members. The complete narrative can be found at nlp-city.vercel.app. M.Eng. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ NLP City Thesis application/pdf Master Master of Engineering in Electrical Engineering and Computer Science Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d3e7b4f8-681c-427c-b1f1-be30a5acc236"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>NLP City</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2024-02</PublicationDate> <Authors> <Author> <DisplayName>Nguyen, Thanh P. Q.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>The rapid advancements in Artificial Intelligence (AI) have led to the development of complex and powerful models, resulting in opaque “black boxes” that hinder human understanding of their decision-making processes. This is especially true in the field of Natural Language Processing as large language models have become widely used and popularized in the form of chatbots and AI assistants. While there have been many attempts at explaining these models and concepts, most of them are directed at an audience already familiar with machine learning concepts. In this paper, I propose an approach to understanding existing concepts and models in NLP by simplifying them into intuitive narratives of towns and cities. By leveraging this more familiar context, the hope is to provide more engagement and information retention to non-technical audience members. The complete narrative can be found at nlp-city.vercel.app.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>