2026-09-19T04:08:39Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1119232022-07-22T14:31:55Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Regina Barzilay.
Luo, Jiaming, (Scientist in Electrical Engineering and Computer Science) Massachusetts Institute of Technology
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2017-10-18T15:10:12Z
2017-10-18T15:10:12Z
2017
2017
http://hdl.handle.net/1721.1/111923
1005706642
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 39-41).
This thesis focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.
by Jiaming Luo.
S.M.
41 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.
Unsupervised learning of morphological forests
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2491bc07-2876-48e5-9976-1b63c6de6ce1">
<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>Unsupervised learning of morphological forests</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2017</PublicationDate>
<Authors>
<Author>
<DisplayName>Luo, Jiaming, (Scientist in Electrical Engineering and Computer Science) Massachusetts Institute of Technology</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>This thesis focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>