Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Libraries
  3. MIT Theses
  4. Graduate Theses
  5. Few-Shot Semi-Supervised Robust Text Classification with MAML

Few-Shot Semi-Supervised Robust Text Classification with MAML

Thumbnail Image
Download
Name

Kang-ikang-meng-eecs-2021-thesis.pdf

Description
Thesis PDF
Size

445.87 KB

Format

Adobe PDF

Checksum (MD5)

9ca073e230703bbc144d39510b6d7f2a

Author(s)
Kang, Isabella
Advisor(s)
Wornell, Gregory
Date Issued
June 2021
Publisher
Massachusetts Institute of Technology
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
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
http://rightsstatements.org/page/InC-EDU/1.0/
Copyright MIT
Persistent DSpace Link
https://hdl.handle.net/1721.1/139260
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.