Using Universal Linguistic Knowledge to Guide Grammar Induction
URL to papers list on conference site
| প্রধান লেখক: | , , , |
|---|---|
| অন্যান্য লেখক: | |
| বিন্যাস: | প্রবন্ধ |
| ভাষা: | en_US |
| প্রকাশিত: |
2011
|
| অনলাইন ব্যবহার করুন: | http://hdl.handle.net/1721.1/63155 https://orcid.org/0000-0002-2921-8201 |
| _version_ | 1826204508985753600 |
|---|---|
| author | Naseem, Tahira Chen, Harr Barzilay, Regina Johnson, Mark |
| 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 Chen, Harr Barzilay, Regina Johnson, Mark |
| author_sort | Naseem, Tahira |
| collection | MIT |
| description | URL to papers list on conference site |
| first_indexed | 2024-09-23T12:56:44Z |
| format | Article |
| id | mit-1721.1/63155 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:56:44Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | mit-1721.1/631552022-09-28T11:02:37Z Using Universal Linguistic Knowledge to Guide Grammar Induction Naseem, Tahira Chen, Harr Barzilay, Regina Johnson, Mark 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 Chen, Harr Naseem, Tahira URL to papers list on conference site We present an approach to grammar induction that utilizes syntactic universals to improve dependency parsing across a range of languages. Our method uses a single set of manually-specified language-independent rules that identify syntactic dependencies between pairs of syntactic categories that commonly occur across languages. During inference of the probabilistic model, we use posterior expectation constraints to require that a minimum proportion of the dependencies we infer be instances of these rules. We also automatically refine the syntactic categories given in our coarsely tagged input. Across six languages our approach outperforms state-of-the-art unsupervised methods by a significant margin. National Science Foundation (U.S.) (CAREER grant IIS-0448168) National Science Foundation (U.S.) (grant IIS-0904684) National Science Foundation (U.S.) (Graduate Research Fellowship) 2011-05-31T20:55:03Z 2011-05-31T20:55:03Z 2010-10 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/63155 Naseem, Tahira et al. "Using Universal Linguistic Knowledge to Guide Grammar Induction." Proceedings of EMNLP 2010: Conference on Empirical Methods in Natural Language Processing, October 9-11, 2010, MIT, Massachusetts, USA. https://orcid.org/0000-0002-2921-8201 en_US http://www.lsi.upc.edu/events/emnlp2010/papers.html Proceedings of EMNLP 2010: Conference on Empirical Methods in Natural Language Processing Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf MIT web domain |
| spellingShingle | Naseem, Tahira Chen, Harr Barzilay, Regina Johnson, Mark Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title | Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title_full | Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title_fullStr | Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title_full_unstemmed | Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title_short | Using Universal Linguistic Knowledge to Guide Grammar Induction |
| title_sort | using universal linguistic knowledge to guide grammar induction |
| url | http://hdl.handle.net/1721.1/63155 https://orcid.org/0000-0002-2921-8201 |
| work_keys_str_mv | AT naseemtahira usinguniversallinguisticknowledgetoguidegrammarinduction AT chenharr usinguniversallinguisticknowledgetoguidegrammarinduction AT barzilayregina usinguniversallinguisticknowledgetoguidegrammarinduction AT johnsonmark usinguniversallinguisticknowledgetoguidegrammarinduction |