A graph-based framework for information extraction
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/122765 |
| _version_ | 1826205196294815744 |
|---|---|
| author | Qian, Yujie (Computer scientist) |
| author2 | Regina Barzilay. |
| author_facet | Regina Barzilay. Qian, Yujie (Computer scientist) |
| author_sort | Qian, Yujie (Computer scientist) |
| collection | MIT |
| description | Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 |
| first_indexed | 2024-09-23T13:09:12Z |
| format | Thesis |
| id | mit-1721.1/122765 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T13:09:12Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1227652023-10-17T13:04:03Z A graph-based framework for information extraction Qian, Yujie (Computer scientist) Regina Barzilay. 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., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 43-45). Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuable source of information to improve predictions. In this thesis, we introduce a graph-based framework (GraphIE) that operates over a graph representing a broad set of dependencies between textual units (i.e. words or sentences). The algorithm propagates information between connected nodes through graph convolutions, generating a richer representation that can be exploited to improve word-level predictions. Evaluation on three different tasks -- namely textual, social media and visual information extraction -- shows that GraphlE consistently outperforms the state-of-the-art sequence tagging model by a significant margin. by Yujie Qian. S.M. S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-11-04T20:23:13Z 2019-11-04T20:23:13Z 2019 2019 Thesis https://hdl.handle.net/1721.1/122765 1124957696 eng 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 45 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Qian, Yujie (Computer scientist) A graph-based framework for information extraction |
| title | A graph-based framework for information extraction |
| title_full | A graph-based framework for information extraction |
| title_fullStr | A graph-based framework for information extraction |
| title_full_unstemmed | A graph-based framework for information extraction |
| title_short | A graph-based framework for information extraction |
| title_sort | graph based framework for information extraction |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/122765 |
| work_keys_str_mv | AT qianyujiecomputerscientist agraphbasedframeworkforinformationextraction AT qianyujiecomputerscientist graphbasedframeworkforinformationextraction |