Learning precise partial semantic mappings via linear algebra
Thesis: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | eng |
Published: |
Massachusetts Institute of Technology
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/106099 |
_version_ | 1811091455120244736 |
---|---|
author | Khani, Fereshte |
author2 | Martin Rinard. |
author_facet | Martin Rinard. Khani, Fereshte |
author_sort | Khani, Fereshte |
collection | MIT |
description | Thesis: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016. |
first_indexed | 2024-09-23T15:02:40Z |
format | Thesis |
id | mit-1721.1/106099 |
institution | Massachusetts Institute of Technology |
language | eng |
last_indexed | 2024-09-23T15:02:40Z |
publishDate | 2016 |
publisher | Massachusetts Institute of Technology |
record_format | dspace |
spelling | mit-1721.1/1060992019-04-10T11:18:17Z Learning precise partial semantic mappings via linear algebra Khani, Fereshte Martin Rinard. 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: S.M. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016. Cataloged from PDF version of thesis. Includes bibliographical references (pages 41-42). In natural language interfaces, having high precision, i.e., abstaining when the system is unsure, is critical for good user experience. However, most NLP systems are trained to maximize accuracy with precision as an afterthought. In this thesis, we put precision first and ask: Can we learn to map parts of the sentence to logical predicates with absolute certainty? To tackle this question, we model semantic mappings from words to predicates as matrices, which allows us to reason efficiently over the entire space of semantic mappings consistent with the training data. We prove that our method obtains 100% precision. Empirically, we demonstrate the effectiveness of our approach on the GeoQuery dataset. by Fereshte Khani. S.M. in Computer Science and Engineering 2016-12-22T16:28:57Z 2016-12-22T16:28:57Z 2016 2016 Thesis http://hdl.handle.net/1721.1/106099 965386321 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 42 pages application/pdf Massachusetts Institute of Technology |
spellingShingle | Electrical Engineering and Computer Science. Khani, Fereshte Learning precise partial semantic mappings via linear algebra |
title | Learning precise partial semantic mappings via linear algebra |
title_full | Learning precise partial semantic mappings via linear algebra |
title_fullStr | Learning precise partial semantic mappings via linear algebra |
title_full_unstemmed | Learning precise partial semantic mappings via linear algebra |
title_short | Learning precise partial semantic mappings via linear algebra |
title_sort | learning precise partial semantic mappings via linear algebra |
topic | Electrical Engineering and Computer Science. |
url | http://hdl.handle.net/1721.1/106099 |
work_keys_str_mv | AT khanifereshte learningprecisepartialsemanticmappingsvialinearalgebra |