Few-shot text classification with distributional signatures
Name
1241198010-MIT.pdf
Size
1.07 MB
Format
Adobe PDF
Checksum (MD5)
1ea594e6f503f3f99c78055f69925734
Author(s)
Wu, Menghua(Data scientist)Massachusetts Institute of Technology.
Advisor(s)
Regina Barzilay.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
We explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text is challenging-lexical features highly informative for one task may be insignificant for another. Thus, rather than learning solely from words, our model also leverages their distributional signatures, which encode pertinent word occurrence patterns. Our model is trained within a meta-learning framework to map these signatures into attention scores, which are then used to weight the lexical representations of words. We demonstrate that our model consistently outperforms prototypical networks learned on lexical knowledge (Snell et al., 2017) in both few-shot text classification and relation classification by a significant margin across six benchmark datasets (20.0% on average in 1-shot classification).
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Date of graduation confirmed by MIT Registrar Office. "May 2020." Cataloged from student-submitted PDF of thesis.
Includes bibliographical references (pages 18-21).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
