2026-09-19T15:39:24Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1061182026-06-06T00:49:13Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Regina Barzilay.
Joshi, Hrishikesh S
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2016-12-22T16:29:44Z
2016-12-22T16:29:44Z
2016
2016
http://hdl.handle.net/1721.1/106118
965799043
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 47-51).
Question answering forums are rapidly growing in size with no automated ability to refer to and reuse existing answers. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations are scarce and fragmented, driven largely by participants. We design a novel combination of recurrent and convolutional models (gated convolutions) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields a 10% gain over a standard IR baseline, and a 6% gain over standard neural network architectures (including CNNs and LSTMs) trained analogously.
by Hrishikesh S. Joshi.
M.Eng.
51 pages
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Finding similar questions in large-scale community QA forums
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="37057a28-a3a6-4b31-ab27-2cabb05e18e8">
<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>Finding similar questions in large-scale community QA forums</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2016</PublicationDate>
<Authors>
<Author>
<DisplayName>Joshi, Hrishikesh S</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>Question answering forums are rapidly growing in size with no automated ability to refer to and reuse existing answers. In this paper, we develop a methodology for finding semantically related questions. The task is difficult since 1) key pieces of information are often buried in extraneous details in the question body and 2) available annotations are scarce and fragmented, driven largely by participants. We design a novel combination of recurrent and convolutional models (gated convolutions) to effectively map questions to their semantic representations. The models are pre-trained within an encoder-decoder framework (from body to title) on the basis of the entire raw corpus, and fine-tuned discriminatively from limited annotations. Our evaluation demonstrates that our model yields a 10% gain over a standard IR baseline, and a 6% gain over standard neural network architectures (including CNNs and LSTMs) trained analogously.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>