2026-09-19T13:15:47Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1216302026-06-06T00:49:08Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Karthik Dinakar and Roger Levy.
Manna, Amin(Amin A.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2019-07-15T20:29:26Z
2019-07-15T20:29:26Z
2018
2018
https://hdl.handle.net/1721.1/121630
1098174661
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 81-84).
Language models and semantic word embeddings have become ubiquitous as sources for machine learning features in a wide range of predictive tasks and real-world applications. We argue that language models trained on a corpus of text can learn the linguistic biases implicit in that corpus. We discuss linguistic biases, or differences in identity and perspective that account for the variation in language use from one speaker to another. We then describe methods to intentionally capture "linguistic lenses": computational representations of these perspectives. We show how the captured lenses can be used to guide machine learning models during training. We define a number of lenses for author-to-author similarity and word-to-word interchangeability. We demonstrate how lenses can be used during training time to imbue language models with perspectives about writing style, or to create lensed language models that learn less linguistic gender bias than their un-lensed counterparts.
by Amin Manna.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
84 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Deep linguistic lensing
Thesis
application/pdf
2019-07-15T20:29:22Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2ea8b8fa-8474-49d8-8c86-809a8d83b4b5">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Deep linguistic lensing</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2018</PublicationDate>
<Authors>
<Author>
<DisplayName>Manna, Amin(Amin A.)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Language models and semantic word embeddings have become ubiquitous as sources for machine learning features in a wide range of predictive tasks and real-world applications. We argue that language models trained on a corpus of text can learn the linguistic biases implicit in that corpus. We discuss linguistic biases, or differences in identity and perspective that account for the variation in language use from one speaker to another. We then describe methods to intentionally capture "linguistic lenses": computational representations of these perspectives. We show how the captured lenses can be used to guide machine learning models during training. We define a number of lenses for author-to-author similarity and word-to-word interchangeability. We demonstrate how lenses can be used during training time to imbue language models with perspectives about writing style, or to create lensed language models that learn less linguistic gender bias than their un-lensed counterparts.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>