Deriving machine attention from human rationales
Name
1126661737-MIT.pdf
Size
4.06 MB
Format
Adobe PDF
Checksum (MD5)
6b918ad1320e9c985782b58c29ee9d51
Author(s)
Bao, Yujia.
Advisor(s)
Regina Barzilay.
Date Issued
2019
Publisher
Massachusetts Institute of Technology
Abstract
Attention-based models are successful when trained on large amounts of data. In this thesis, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated rationales and map them into continuous attention. Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones. Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention. Our empirical results validate this hypothesis and show that our approach delivers significant gains over state-of-the-art baselines, yielding over 15% average error reduction on benchmark datasets. Our code and data are available at https: //github. com/YujiaBao/R2A.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 47-50).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
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.
Persistent DSpace Link
