Using semantic cues to learn syntax
We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide useful clues about the underlying syntactic structure, and they are readily available in many domains (e.g., info-boxes a...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for the Advancement of Artificial Intelligence
2012
|
| Online Access: | http://hdl.handle.net/1721.1/74108 https://orcid.org/0000-0002-2921-8201 |
| _version_ | 1826204824961548288 |
|---|---|
| author | Naseem, Tahira Barzilay, Regina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Naseem, Tahira Barzilay, Regina |
| author_sort | Naseem, Tahira |
| collection | MIT |
| description | We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide useful
clues about the underlying syntactic structure, and they are readily available in many domains (e.g., info-boxes and HTML markup). Our method is based on the intuition that syntactic realizations of the same semantic predicate exhibit some degree of consistency. We incorporate this intuition in
a directed graphical model that tightly links the syntactic and semantic structures. This design enables us to exploit syntactic regularities while still allowing for variations. Another strength of the model lies in its ability to capture non-local dependency relations. Our results demonstrate that even a small amount of semantic annotations greatly improves the accuracy of learned dependencies when tested on both in-domain and out-of-domain texts. |
| first_indexed | 2024-09-23T13:01:40Z |
| format | Article |
| id | mit-1721.1/74108 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:01:40Z |
| publishDate | 2012 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | mit-1721.1/741082022-09-28T11:33:55Z Using semantic cues to learn syntax Naseem, Tahira Barzilay, Regina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Barzilay, Regina Barzilay, Regina Naseem, Tahira We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide useful clues about the underlying syntactic structure, and they are readily available in many domains (e.g., info-boxes and HTML markup). Our method is based on the intuition that syntactic realizations of the same semantic predicate exhibit some degree of consistency. We incorporate this intuition in a directed graphical model that tightly links the syntactic and semantic structures. This design enables us to exploit syntactic regularities while still allowing for variations. Another strength of the model lies in its ability to capture non-local dependency relations. Our results demonstrate that even a small amount of semantic annotations greatly improves the accuracy of learned dependencies when tested on both in-domain and out-of-domain texts. United States. Defense Advanced Research Projects Agency (Defense Advanced Research Projects Agency (DARPA) Machine Reading Program under Air Force Research Laboratory (AFRL) prime contract no. FA8750-09-C-0172) United States. Defense Advanced Research Projects Agency (Air Force Research Laboratory (AFRL) prime contract no. FA8750-09-C-0172) U.S. Army Research Laboratory (contract no. W911NF-10-1-0533) 2012-10-18T19:36:54Z 2012-10-18T19:36:54Z 2011-08 Article http://purl.org/eprint/type/ConferencePaper 1577355075 9781577355076 http://hdl.handle.net/1721.1/74108 Naseem, Tahira and Regina Barzilay."Using semantic cues to learn syntax." Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, Hyatt Regency San Francisco, August 7–11, 2011, USA. https://orcid.org/0000-0002-2921-8201 en_US http://www.aaai.org/ocs/index.php/AAAI/AAAI11/paper/view/3741/3975 Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011 Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Association for the Advancement of Artificial Intelligence MIT web domain |
| spellingShingle | Naseem, Tahira Barzilay, Regina Using semantic cues to learn syntax |
| title | Using semantic cues to learn syntax |
| title_full | Using semantic cues to learn syntax |
| title_fullStr | Using semantic cues to learn syntax |
| title_full_unstemmed | Using semantic cues to learn syntax |
| title_short | Using semantic cues to learn syntax |
| title_sort | using semantic cues to learn syntax |
| url | http://hdl.handle.net/1721.1/74108 https://orcid.org/0000-0002-2921-8201 |
| work_keys_str_mv | AT naseemtahira usingsemanticcuestolearnsyntax AT barzilayregina usingsemanticcuestolearnsyntax |