2026-09-19T20:44:05Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1228782021-07-05T14:03:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Regina Barzilay.
Bao, Yujia.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2019-11-12T17:41:08Z
2019-11-12T17:41:08Z
2019
2019
https://hdl.handle.net/1721.1/122878
1126661737
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).
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.
by Yujia Bao.
S.M.
S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
50 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.
Deriving machine attention from human rationales
Thesis
application/pdf
2019-11-12T17:41:07Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d76debb9-c4a0-4740-8d58-804fc8b142c1">
<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>Deriving machine attention from human rationales</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Bao, Yujia.</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>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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>