2026-09-19T02:24:01Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1392602022-01-15T03:50:06Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Wornell, Gregory
Kang, Isabella
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-01-14T15:00:02Z
2022-01-14T15:00:02Z
2021-06
2021-06-17T20:13:27.817Z
https://hdl.handle.net/1721.1/139260
The need for few-shot semi-supervised text classification arises in a variety of applications, including, e.g., recommendation systems classifying textual content such as product descriptions or news articles based on limited amounts of user feedback. In such settings, existing supervised methods lack a way to leverage unlabeled data, which may be available in larger amounts.
We develop a method for improving the accuracy and robustness of a supervised meta-learning algorithm (Model-Agnostic Meta-Learning) applied to few-shot natural language text classification tasks. We also detail a way to incorporate semi-supervised learning into MAML by designing a procedure to create self-supervised tasks from unlabeled text examples. We present the test accuracies in experimental results for sentiment classification and topic classification. As a representative example, we achieved gains in accuracy ranging from 1% to 3% on Amazon review and news headline datasets
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Few-Shot Semi-Supervised Robust Text Classification with MAML
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="4905a78d-7714-495d-a6d1-8c5fae601093">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Few-Shot Semi-Supervised Robust Text Classification with MAML</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2021-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Kang, Isabella</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>The need for few-shot semi-supervised text classification arises in a variety of applications, including, e.g., recommendation systems classifying textual content such as product descriptions or news articles based on limited amounts of user feedback. In such settings, existing supervised methods lack a way to leverage unlabeled data, which may be available in larger amounts.
We develop a method for improving the accuracy and robustness of a supervised meta-learning algorithm (Model-Agnostic Meta-Learning) applied to few-shot natural language text classification tasks. We also detail a way to incorporate semi-supervised learning into MAML by designing a procedure to create self-supervised tasks from unlabeled text examples. We present the test accuracies in experimental results for sentiment classification and topic classification. As a representative example, we achieved gains in accuracy ranging from 1% to 3% on Amazon review and news headline datasets</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>