Learning a semantic database from unstructured text
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, June 2014.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2014
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/91443 |
| _version_ | 1826202224505651200 |
|---|---|
| author | Dhandhania, Keshav |
| author2 | Tommi Jaakkola. |
| author_facet | Tommi Jaakkola. Dhandhania, Keshav |
| author_sort | Dhandhania, Keshav |
| collection | MIT |
| description | Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, June 2014. |
| first_indexed | 2024-09-23T12:04:08Z |
| format | Thesis |
| id | mit-1721.1/91443 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T12:04:08Z |
| publishDate | 2014 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/914432019-04-10T16:18:20Z Learning a semantic database from unstructured text Dhandhania, Keshav Tommi Jaakkola. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, June 2014. 24 "May 23, 2014." Cataloged from PDF version of thesis. Includes bibliographical references (pages 35-38). In this paper, we aim to learn a semantic database given a text corpus. Specifically, we focus on predicting whether or not a pair of entities are related by the hypernym relation, also known as the 'is-a' or 'type-of' relation. We learn a neural network model for this task. The model is given as input a description of the words and the context from the text corpus in which a pair of nouns (entities) occur. In particular, among other things the description includes pre-trained embeddings of the words. We show that the model is able to predict hypernym noun pairs even though the dataset includes many incorrectly labeled noun pairs. Finally, we suggest ways to improve the dataset and the method. by Keshav Dhandhania. M. Eng. 2014-11-04T21:37:04Z 2014-11-04T21:37:04Z 2014 Thesis http://hdl.handle.net/1721.1/91443 893679084 eng 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 38 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Dhandhania, Keshav Learning a semantic database from unstructured text |
| title | Learning a semantic database from unstructured text |
| title_full | Learning a semantic database from unstructured text |
| title_fullStr | Learning a semantic database from unstructured text |
| title_full_unstemmed | Learning a semantic database from unstructured text |
| title_short | Learning a semantic database from unstructured text |
| title_sort | learning a semantic database from unstructured text |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/91443 |
| work_keys_str_mv | AT dhandhaniakeshav learningasemanticdatabasefromunstructuredtext |